1 |
9 |
Bootstrapped Meta-Learning |
10, 8, 10, 8 |
Accept (Oral) |
2 |
8.67 |
A Fine-Grained Analysis on Distribution Shift |
8, 10, 8 |
Accept (Oral) |
3 |
8.67 |
Diffusion-Based Voice Conversion with Fast Maximum Likelihood Sampling Scheme |
8, 8, 10 |
Accept (Oral) |
4 |
8.67 |
Self-Supervision Enhanced Feature Selection with Correlated Gates |
10, 8, 8 |
Accept (Spotlight) |
5 |
8.67 |
Filtered-CoPhy: Unsupervised Learning of Counterfactual Physics in Pixel Space |
8, 8, 10 |
Accept (Oral) |
6 |
8.67 |
Towards a Unified View of Parameter-Efficient Transfer Learning |
10, 8, 8 |
Accept (Spotlight) |
7 |
8.5 |
Neural Structured Prediction for Inductive Node Classification |
8, 8, 10, 8 |
Accept (Oral) |
8 |
8.5 |
Score-Based Generative Modeling with Critically-Damped Langevin Diffusion |
8, 8, 10, 8 |
Accept (Spotlight) |
9 |
8.5 |
Understanding over-squashing and bottlenecks on graphs via curvature |
8, 8, 10, 8 |
Accept (Oral) |
10 |
8.5 |
DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS |
8, 10, 8, 8 |
Accept (Oral) |
11 |
8.5 |
Expressiveness and Approximation Properties of Graph Neural Networks |
10, 8, 8, 8 |
Accept (Oral) |
12 |
8.5 |
Scaling Laws for Neural Machine Translation |
8, 8, 10, 8 |
Accept (Spotlight) |
13 |
8.5 |
Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation |
10, 8, 8, 8 |
Accept (Spotlight) |
14 |
8.5 |
What Happens after SGD Reaches Zero Loss? --A Mathematical Framework |
8, 8, 8, 10 |
Accept (Spotlight) |
15 |
8 |
Fine-Tuning Distorts Pretrained Features and Underperforms Out-of-Distribution |
8, 8, 8, 8 |
Accept (Oral) |
16 |
8 |
Probabilistic Implicit Scene Completion |
8, 8, 8, 8, 8 |
Accept (Spotlight) |
17 |
8 |
The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design |
8, 8, 8, 8, 8 |
Accept (Spotlight) |
18 |
8 |
Natural Language Descriptions of Deep Features |
8, 8, 8 |
Accept (Oral) |
19 |
8 |
Real-Time Neural Voice Camouflage |
8, 8, 8 |
Accept (Oral) |
20 |
8 |
Fast Differentiable Matrix Square Root |
8, 8, 8 |
Accept (Poster) |
21 |
8 |
On the Optimal Memorization Power of ReLU Neural Networks |
8, 8, 8 |
Accept (Spotlight) |
22 |
8 |
Evaluating Distributional Distortion in Neural Language Modeling |
8, 8, 8 |
Accept (Poster) |
23 |
8 |
A General Analysis of Example-Selection for Stochastic Gradient Descent |
8, 8, 8, 8 |
Accept (Spotlight) |
24 |
8 |
Meta-Learning with Fewer Tasks through Task Interpolation |
8, 8, 8, 8, 8 |
Accept (Oral) |
25 |
8 |
Language modeling via stochastic processes |
8, 8, 8, 8 |
Accept (Oral) |
26 |
8 |
Vision-Based Manipulators Need to Also See from Their Hands |
8, 8, 8 |
Accept (Oral) |
27 |
8 |
The Hidden Convex Optimization Landscape of Regularized Two-Layer ReLU Networks: an Exact Characterization of Optimal Solutions |
8, 8, 8, 8 |
Accept (Oral) |
28 |
8 |
Task Relatedness-Based Generalization Bounds for Meta Learning |
8, 8, 8, 8 |
Accept (Spotlight) |
29 |
8 |
GNN-LM: Language Modeling based on Global Contexts via GNN |
8, 10, 6 |
Accept (Spotlight) |
30 |
8 |
Programmatic Reinforcement Learning without Oracles |
8, 8, 8 |
Accept (Spotlight) |
31 |
8 |
Ab-Initio Potential Energy Surfaces by Pairing GNNs with Neural Wave Functions |
8, 8, 8 |
Accept (Spotlight) |
32 |
8 |
Efficiently Modeling Long Sequences with Structured State Spaces |
8, 8, 8 |
Accept (Oral) |
33 |
8 |
Rethinking the Representational Continuity: Towards Unsupervised Continual Learning |
8, 8, 8, 8 |
Accept (Oral) |
34 |
8 |
Unsupervised Vision-Language Grammar Induction with Shared Structure Modeling |
8, 8, 8 |
Accept (Oral) |
35 |
8 |
Assessing Generalization of SGD via Disagreement |
8, 8, 8, 8 |
Accept (Spotlight) |
36 |
8 |
Poisoning and Backdooring Contrastive Learning |
8, 8, 8, 8 |
Accept (Oral) |
37 |
8 |
NeuPL: Neural Population Learning |
8, 8, 8, 8 |
Accept (Poster) |
38 |
8 |
Neural Deep Equilibrium Solvers |
8, 8, 8 |
Accept (Poster) |
39 |
8 |
Hyperparameter Tuning with Renyi Differential Privacy |
8, 6, 8, 10 |
Accept (Oral) |
40 |
8 |
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics |
8, 8, 8, 8 |
Accept (Oral) |
41 |
8 |
Byzantine-Robust Learning on Heterogeneous Datasets via Bucketing |
6, 8, 8, 10 |
Accept (Spotlight) |
42 |
8 |
EntQA: Entity Linking as Question Answering |
8, 8, 8 |
Accept (Spotlight) |
43 |
8 |
MT3: Multi-Task Multitrack Music Transcription |
8, 8, 8, 8 |
Accept (Spotlight) |
44 |
8 |
BEiT: BERT Pre-Training of Image Transformers |
8, 8, 8, 8 |
Accept (Oral) |
45 |
8 |
MIDI-DDSP: Detailed Control of Musical Performance via Hierarchical Modeling |
8, 8, 8 |
Accept (Oral) |
46 |
8 |
RotoGrad: Gradient Homogenization in Multitask Learning |
8, 8, 8, 8 |
Accept (Spotlight) |
47 |
8 |
Inductive Relation Prediction Using Analogy Subgraph Embeddings |
8, 8, 8, 8, 8 |
Accept (Poster) |
48 |
8 |
Wiring Up Vision: Minimizing Supervised Synaptic Updates Needed to Produce a Primate Ventral Stream |
8, 8, 8, 8 |
Accept (Spotlight) |
49 |
8 |
RelaxLoss: Defending Membership Inference Attacks without Losing Utility |
8, 8, 8 |
Accept (Spotlight) |
50 |
8 |
Spike-inspired rank coding for fast and accurate recurrent neural networks |
8, 8, 8 |
Accept (Spotlight) |
51 |
8 |
Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking |
8, 8, 8 |
Accept (Spotlight) |
52 |
8 |
EViT: Expediting Vision Transformers via Token Reorganizations |
8, 8, 8, 8 |
Accept (Spotlight) |
53 |
8 |
Meta Discovery: Learning to Discover Novel Classes given Very Limited Data |
8, 8, 8, 8 |
Accept (Spotlight) |
54 |
8 |
Explanations of Black-Box Models based on Directional Feature Interactions |
8, 8, 8, 8 |
Accept (Spotlight) |
55 |
8 |
Perceiver IO: A General Architecture for Structured Inputs & Outputs |
8, 8, 8, 8 |
Accept (Spotlight) |
56 |
8 |
Towards Deployment-Efficient Reinforcement Learning: Lower Bound and Optimality |
8, 8, 8, 8 |
Accept (Spotlight) |
57 |
8 |
Granger causal inference on DAGs identifies genomic loci regulating transcription |
8, 8, 8, 8 |
Accept (Poster) |
58 |
8 |
Finetuned Language Models are Zero-Shot Learners |
8, 8, 8, 8 |
Accept (Oral) |
59 |
8 |
Emergent Communication at Scale |
8, 8, 8, 8 |
Accept (Spotlight) |
60 |
8 |
Data-Efficient Graph Grammar Learning for Molecular Generation |
8, 8, 8, 8 |
Accept (Oral) |
61 |
8 |
DemoDICE: Offline Imitation Learning with Supplementary Imperfect Demonstrations |
8, 8, 8 |
Accept (Poster) |
62 |
8 |
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models |
8, 8, 8, 8, 8 |
Accept (Oral) |
63 |
8 |
PER-ETD: A Polynomially Efficient Emphatic Temporal Difference Learning Method |
8, 8, 8, 8 |
Accept (Poster) |
64 |
8 |
A New Perspective on "How Graph Neural Networks Go Beyond Weisfeiler-Lehman?" |
8, 8, 8, 8 |
Accept (Oral) |
65 |
8 |
Path Auxiliary Proposal for MCMC in Discrete Space |
8, 8, 8, 8 |
Accept (Spotlight) |
66 |
8 |
Tackling the Generative Learning Trilemma with Denoising Diffusion GANs |
8, 8, 8, 8 |
Accept (Spotlight) |
67 |
8 |
AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning |
8, 8, 8, 8 |
Accept (Spotlight) |
68 |
8 |
Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design |
8, 8, 8, 8 |
Accept (Oral) |
69 |
8 |
Scalable Sampling for Nonsymmetric Determinantal Point Processes |
8, 8, 8, 8 |
Accept (Spotlight) |
70 |
8 |
Learning transferable motor skills with hierarchical latent mixture policies |
8, 8, 8, 8 |
Accept (Spotlight) |
71 |
8 |
TAMP-S2GCNets: Coupling Time-Aware Multipersistence Knowledge Representation with Spatio-Supra Graph Convolutional Networks for Time-Series Forecasting |
8, 8, 8 |
Accept (Spotlight) |
72 |
8 |
Reinforcement Learning under a Multi-agent Predictive State Representation Model: Method and Theory |
8, 8, 8 |
Accept (Spotlight) |
73 |
8 |
How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective |
8, 8, 8, 8 |
Accept (Spotlight) |
74 |
8 |
SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models |
8, 8, 8 |
Accept (Spotlight) |
75 |
8 |
Sampling with Mirrored Stein Operators |
8, 6, 10, 8 |
Accept (Spotlight) |
76 |
8 |
Understanding Latent Correlation-Based Multiview Learning and Self-Supervision: An Identifiability Perspective |
8, 8, 8 |
Accept (Spotlight) |
77 |
8 |
Contrastive Label Disambiguation for Partial Label Learning |
8, 8, 8 |
Accept (Oral) |
78 |
8 |
Frame Averaging for Invariant and Equivariant Network Design |
8, 8, 8, 8 |
Accept (Oral) |
79 |
8 |
Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design |
8, 8, 8 |
Accept (Spotlight) |
80 |
8 |
RISP: Rendering-Invariant State Predictor with Differentiable Simulation and Rendering for Cross-Domain Parameter Estimation |
8, 8, 8 |
Accept (Oral) |
81 |
8 |
Progressive Distillation for Fast Sampling of Diffusion Models |
8, 8, 8, 8 |
Accept (Spotlight) |
82 |
8 |
On the Connection between Local Attention and Dynamic Depth-wise Convolution |
8, 8, 8 |
Accept (Spotlight) |
83 |
8 |
Comparing Distributions by Measuring Differences that Affect Decision Making |
8, 8, 8 |
Accept (Oral) |
84 |
8 |
Universal Approximation Under Constraints is Possible with Transformers |
8, 6, 10 |
Accept (Spotlight) |
85 |
8 |
Convergent Graph Solvers |
8, 8, 8, 8 |
Accept (Poster) |
86 |
8 |
The Information Geometry of Unsupervised Reinforcement Learning |
8, 8, 8 |
Accept (Oral) |
87 |
8 |
SphereFace2: Binary Classification is All You Need for Deep Face Recognition |
8, 8, 8 |
Accept (Spotlight) |
88 |
8 |
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks |
8, 8, 8, 8 |
Accept (Spotlight) |
89 |
8 |
Minibatch vs Local SGD with Shuffling: Tight Convergence Bounds and Beyond |
8, 8, 8 |
Accept (Oral) |
90 |
8 |
iLQR-VAE : control-based learning of input-driven dynamics with applications to neural data |
8, 8, 8 |
Accept (Oral) |
91 |
8 |
Asymmetry Learning for Counterfactually-invariant Classification in OOD Tasks |
8, 8, 8 |
Accept (Oral) |
92 |
8 |
Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization |
8, 8, 8 |
Accept (Oral) |
93 |
8 |
Learning Strides in Convolutional Neural Networks |
8, 8, 8, 8 |
Accept (Spotlight) |
94 |
8 |
Adaptive Control Flow in Transformers Improves Systematic Generalization |
8, 8, 8 |
Accept (Poster) |
95 |
8 |
Possibility Before Utility: Learning And Using Hierarchical Affordances |
8, 8, 8, 8 |
Accept (Spotlight) |
96 |
8 |
Visual Representation Learning Does Not Generalize Strongly Within the Same Domain |
8, 8, 8, 8 |
Accept (Poster) |
97 |
8 |
Fast Regression for Structured Inputs |
8, 6, 10 |
Accept (Poster) |
98 |
7.75 |
Planning in Stochastic Environments with a Learned Model |
8, 5, 8, 10 |
Accept (Spotlight) |
99 |
7.75 |
Understanding Domain Randomization for Sim-to-real Transfer |
8, 5, 8, 10 |
Accept (Spotlight) |
100 |
7.6 |
Local Feature Swapping for Generalization in Reinforcement Learning |
8, 8, 8, 6, 8 |
Accept (Poster) |
101 |
7.6 |
Source-Free Adaptation to Measurement Shift via Bottom-Up Feature Restoration |
8, 8, 6, 8, 8 |
Accept (Spotlight) |
102 |
7.5 |
InfinityGAN: Towards Infinite-Pixel Image Synthesis |
8, 8, 8, 6 |
Accept (Poster) |
103 |
7.5 |
Adversarial Rademacher Complexity of Deep Neural Networks |
8, 6, 8, 8 |
Reject |
104 |
7.5 |
SOSP: Efficiently Capturing Global Correlations by Second-Order Structured Pruning |
8, 8, 8, 6 |
Accept (Spotlight) |
105 |
7.5 |
Constrained Policy Optimization via Bayesian World Models |
8, 6, 8, 8 |
Accept (Spotlight) |
106 |
7.5 |
NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy |
8, 6, 8, 8 |
Accept (Poster) |
107 |
7.5 |
Case-based Reasoning for Better Generalization in Text-Adventure Games |
8, 8, 8, 6 |
Accept (Poster) |
108 |
7.5 |
Accelerated Policy Learning with Parallel Differentiable Simulation |
8, 6, 8, 8 |
Accept (Poster) |
109 |
7.5 |
Scalable One-Pass Optimisation of High-Dimensional Weight-Update Hyperparameters by Implicit Differentiation |
8, 6, 8, 8 |
Accept (Spotlight) |
110 |
7.5 |
StyleAlign: Analysis and Applications of Aligned StyleGAN Models |
8, 8, 6, 8 |
Accept (Oral) |
111 |
7.5 |
The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models |
8, 8, 8, 6 |
Accept (Poster) |
112 |
7.5 |
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? |
6, 8, 8, 8 |
Accept (Poster) |
113 |
7.5 |
Imbedding Deep Neural Networks |
6, 8, 8, 8 |
Accept (Spotlight) |
114 |
7.5 |
Sparse Communication via Mixed Distributions |
8, 8, 8, 6 |
Accept (Oral) |
115 |
7.5 |
Conditional Image Generation by Conditioning Variational Auto-Encoders |
8, 6, 8, 8 |
Accept (Poster) |
116 |
7.5 |
Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation |
8, 8, 6, 8 |
Accept (Poster) |
117 |
7.5 |
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools |
8, 10, 6, 6 |
Accept (Poster) |
118 |
7.5 |
Policy improvement by planning with Gumbel |
8, 6, 8, 8 |
Accept (Spotlight) |
119 |
7.5 |
Adversarial Robustness Through the Lens of Causality |
8, 6, 8, 8 |
Accept (Poster) |
120 |
7.5 |
Know Your Action Set: Learning Action Relations for Reinforcement Learning |
8, 8, 6, 8 |
Accept (Poster) |
121 |
7.5 |
How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data |
8, 8, 8, 6 |
Accept (Poster) |
122 |
7.5 |
Decoupled Adaptation for Cross-Domain Object Detection |
6, 8, 8, 8 |
Accept (Poster) |
123 |
7.5 |
Information Prioritization through Empowerment in Visual Model-based RL |
8, 8, 8, 6 |
Accept (Poster) |
124 |
7.5 |
Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks |
6, 8, 8, 8 |
Accept (Spotlight) |
125 |
7.5 |
Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers |
8, 6, 8, 8 |
Accept (Spotlight) |
126 |
7.5 |
Coordination Among Neural Modules Through a Shared Global Workspace |
6, 6, 8, 10 |
Accept (Oral) |
127 |
7.5 |
Learning more skills through optimistic exploration |
8, 8, 8, 6 |
Accept (Spotlight) |
128 |
7.5 |
Large Language Models Can Be Strong Differentially Private Learners |
8, 8, 6, 8 |
Accept (Oral) |
129 |
7.5 |
Meta-Imitation Learning by Watching Video Demonstrations |
8, 8, 8, 6 |
Accept (Poster) |
130 |
7.5 |
Mention Memory: incorporating textual knowledge into Transformers through entity mention attention |
8, 8, 8, 6 |
Accept (Poster) |
131 |
7.5 |
Hybrid Local SGD for Federated Learning with Heterogeneous Communications |
8, 6, 8, 8 |
Accept (Spotlight) |
132 |
7.5 |
HyAR: Addressing Discrete-Continuous Action Reinforcement Learning via Hybrid Action Representation |
8, 8, 6, 8 |
Accept (Poster) |
133 |
7.5 |
Revisiting flow generative models for Out-of-distribution detection |
8, 8, 6, 8 |
Accept (Poster) |
134 |
7.5 |
Training invariances and the low-rank phenomenon: beyond linear networks |
8, 8, 6, 8 |
Accept (Spotlight) |
135 |
7.5 |
Creating Training Sets via Weak Indirect Supervision |
8, 6, 8, 8 |
Accept (Poster) |
136 |
7.5 |
CKConv: Continuous Kernel Convolution For Sequential Data |
8, 8, 8, 6 |
Accept (Poster) |
137 |
7.5 |
What’s Wrong with Deep Learning in Tree Search for Combinatorial Optimization |
8, 6, 8, 8 |
Accept (Poster) |
138 |
7.5 |
Continual Learning with Filter Atom Swapping |
8, 6, 8, 8 |
Accept (Spotlight) |
139 |
7.5 |
CycleMLP: A MLP-like Architecture for Dense Prediction |
8, 8, 6, 8 |
Accept (Oral) |
140 |
7.5 |
Continuous-Time Meta-Learning with Forward Mode Differentiation |
8, 6, 8, 8 |
Accept (Spotlight) |
141 |
7.5 |
Pixelated Butterfly: Simple and Efficient Sparse training for Neural Network Models |
6, 8, 8, 8 |
Accept (Spotlight) |
142 |
7.5 |
CrossBeam: Learning to Search in Bottom-Up Program Synthesis |
8, 8, 6, 8 |
Accept (Poster) |
143 |
7.5 |
Exploring the Limits of Large Scale Pre-training |
8, 6, 8, 8 |
Accept (Spotlight) |
144 |
7.5 |
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception |
8, 8, 8, 6 |
Accept (Poster) |
145 |
7.5 |
Can an Image Classifier Suffice For Action Recognition? |
8, 8, 6, 8 |
Accept (Poster) |
146 |
7.5 |
Vitruvion: A Generative Model of Parametric CAD Sketches |
8, 6, 8, 8 |
Accept (Poster) |
147 |
7.5 |
Weighted Training for Cross-Task Learning |
8, 8, 6, 8 |
Accept (Oral) |
148 |
7.5 |
Deconstructing the Inductive Biases of Hamiltonian Neural Networks |
6, 8, 8, 8 |
Accept (Spotlight) |
149 |
7.5 |
Strength of Minibatch Noise in SGD |
6, 8, 8, 8 |
Accept (Spotlight) |
150 |
7.5 |
A Deep Variational Approach to Clustering Survival Data |
8, 8, 8, 6 |
Accept (Poster) |
151 |
7.5 |
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy |
8, 6, 8, 8 |
Accept (Spotlight) |
152 |
7.5 |
Learning Discrete Structured Variational Auto-Encoder using Natural Evolution Strategies |
8, 6, 8, 8 |
Accept (Poster) |
153 |
7.5 |
On the Pitfalls of Analyzing Individual Neurons in Language Models |
6, 8, 8, 8 |
Accept (Poster) |
154 |
7.5 |
LORD: Lower-Dimensional Embedding of Log-Signature in Neural Rough Differential Equations |
8, 8, 6, 8 |
Accept (Poster) |
155 |
7.5 |
Understanding the Role of Self Attention for Efficient Speech Recognition |
8, 6, 8, 8 |
Accept (Spotlight) |
156 |
7.5 |
TAPEX: Table Pre-training via Learning a Neural SQL Executor |
6, 8, 8, 8 |
Accept (Poster) |
157 |
7.5 |
$\pi$BO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization |
8, 6, 8, 8 |
Accept (Poster) |
158 |
7.5 |
Denoising Likelihood Score Matching for Conditional Score-based Data Generation |
8, 8, 6, 8 |
Accept (Poster) |
159 |
7.5 |
Interpretable Unsupervised Diversity Denoising and Artefact Removal |
8, 8, 8, 6 |
Accept (Spotlight) |
160 |
7.5 |
PAC-Bayes Information Bottleneck |
6, 10, 8, 6 |
Accept (Spotlight) |
161 |
7.5 |
DEPTS: Deep Expansion Learning for Periodic Time Series Forecasting |
6, 8, 8, 8 |
Accept (Spotlight) |
162 |
7.5 |
StyleNeRF: A Style-based 3D Aware Generator for High-resolution Image Synthesis |
10, 6, 6, 8 |
Accept (Poster) |
163 |
7.5 |
Learnability of convolutional neural networks for infinite dimensional input via mixed and anisotropic smoothness |
6, 8, 8, 8 |
Accept (Spotlight) |
164 |
7.5 |
Extending the WILDS Benchmark for Unsupervised Adaptation |
8, 6, 8, 8 |
Accept (Oral) |
165 |
7.5 |
Relating transformers to models and neural representations of the hippocampal formation |
8, 8, 6, 8 |
Accept (Poster) |
166 |
7.5 |
Environment Predictive Coding for Visual Navigation |
8, 8, 6, 8 |
Accept (Poster) |
167 |
7.5 |
Unsupervised Federated Learning is Possible |
8, 8, 6, 8 |
Accept (Poster) |
168 |
7.5 |
Latent Variable Sequential Set Transformers for Joint Multi-Agent Motion Prediction |
8, 8, 6, 8 |
Accept (Spotlight) |
169 |
7.5 |
UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning |
8, 8, 6, 8 |
Accept (Poster) |
170 |
7.5 |
No One Representation to Rule Them All: Overlapping Features of Training Methods |
8, 8, 8, 6 |
Accept (Poster) |
171 |
7.5 |
Approximation and Learning with Deep Convolutional Models: a Kernel Perspective |
8, 8, 6, 8 |
Accept (Poster) |
172 |
7.5 |
Generative Models as a Data Source for Multiview Representation Learning |
8, 8, 8, 6 |
Accept (Poster) |
173 |
7.5 |
On Improving Adversarial Transferability of Vision Transformers |
6, 8, 8, 8 |
Accept (Spotlight) |
174 |
7.5 |
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training Quantization |
8, 6, 8, 8 |
Accept (Poster) |
175 |
7.5 |
Label Encoding for Regression Networks |
8, 8, 6, 8 |
Accept (Spotlight) |
176 |
7.5 |
Optimization and Adaptive Generalization of Three layer Neural Networks |
6, 8, 8, 8 |
Accept (Poster) |
177 |
7.5 |
Deconfounding to Explanation Evaluation in Graph Neural Networks |
8, 8, 6, 8 |
Reject |
178 |
7.5 |
Unifying Likelihood-free Inference with Black-box Sequence Design and Beyond |
8, 6, 10, 6 |
Accept (Spotlight) |
179 |
7.5 |
Omni-Dimensional Dynamic Convolution |
8, 8, 6, 8 |
Accept (Spotlight) |
180 |
7.5 |
VAE Approximation Error: ELBO and Exponential Families |
6, 8, 8, 8 |
Accept (Spotlight) |
181 |
7.5 |
On the Importance of Firth Bias Reduction in Few-Shot Classification |
8, 8, 8, 6 |
Accept (Spotlight) |
182 |
7.5 |
Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning |
8, 6, 8, 8 |
Accept (Spotlight) |
183 |
7.5 |
Deep Attentive Variational Inference |
8, 8, 8, 6 |
Accept (Poster) |
184 |
7.5 |
Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations |
8, 6, 8, 8 |
Accept (Poster) |
185 |
7.5 |
Efficient Sharpness-aware Minimization for Improved Training of Neural Networks |
8, 8, 6, 8 |
Accept (Poster) |
186 |
7.5 |
Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent |
8, 8, 8, 6 |
Accept (Poster) |
187 |
7.5 |
Learning Super-Features for Image Retrieval |
8, 6, 8, 8 |
Accept (Poster) |
188 |
7.4 |
You Mostly Walk Alone: Analyzing Feature Attribution in Trajectory Prediction |
5, 8, 6, 10, 8 |
Accept (Poster) |
189 |
7.33 |
Convergent and Efficient Deep Q Learning Algorithm |
6, 10, 6 |
Accept (Poster) |
190 |
7.33 |
Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection |
8, 6, 8 |
Accept (Poster) |
191 |
7.33 |
Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics |
6, 8, 8 |
Accept (Spotlight) |
192 |
7.33 |
A Johnson-Lindenstrauss Framework for Randomly Initialized CNNs |
8, 8, 6 |
Accept (Poster) |
193 |
7.33 |
8-bit Optimizers via Block-wise Quantization |
8, 8, 6 |
Accept (Spotlight) |
194 |
7.33 |
Sound Adversarial Audio-Visual Navigation |
8, 8, 6 |
Accept (Poster) |
195 |
7.33 |
Autoregressive Quantile Flows for Predictive Uncertainty Estimation |
8, 8, 6 |
Accept (Spotlight) |
196 |
7.33 |
Learning Causal Relationships from Conditional Moment Restrictions by Importance Weighting |
6, 8, 8 |
Accept (Spotlight) |
197 |
7.33 |
Superclass-Conditional Gaussian Mixture Model For Learning Fine-Grained Embeddings |
8, 8, 6 |
Accept (Spotlight) |
198 |
7.33 |
Graphon based Clustering and Testing of Networks: Algorithms and Theory |
8, 6, 8 |
Accept (Poster) |
199 |
7.33 |
Training Structured Neural Networks Through Manifold Identification and Variance Reduction |
6, 8, 8 |
Accept (Poster) |
200 |
7.33 |
Distributional Decision Transformer for Hindsight Information Matching |
6, 8, 8 |
Accept (Spotlight) |
201 |
7.33 |
On the approximation properties of recurrent encoder-decoder architectures |
6, 8, 8 |
Accept (Spotlight) |
202 |
7.33 |
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation |
6, 8, 8 |
Accept (Poster) |
203 |
7.33 |
Training Data Generating Networks: Shape Reconstruction via Bi-level Optimization |
8, 6, 8 |
Accept (Poster) |
204 |
7.33 |
Discovering Invariant Rationales for Graph Neural Networks |
6, 8, 8 |
Accept (Poster) |
205 |
7.33 |
Open-Set Recognition: A Good Closed-Set Classifier is All You Need |
8, 6, 8 |
Accept (Oral) |
206 |
7.33 |
Delaunay Component Analysis for Evaluation of Data Representations |
6, 8, 8 |
Accept (Poster) |
207 |
7.33 |
Label-Efficient Semantic Segmentation with Diffusion Models |
6, 8, 8 |
Accept (Poster) |
208 |
7.33 |
Bregman Gradient Policy Optimization |
8, 6, 8 |
Accept (Poster) |
209 |
7.33 |
Near-Optimal Reward-Free Exploration for Linear Mixture MDPs with Plug-in Solver |
8, 6, 8 |
Accept (Spotlight) |
210 |
7.33 |
Domino: Discovering Systematic Errors with Cross-Modal Embeddings |
8, 8, 6 |
Accept (Oral) |
211 |
7.33 |
Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future |
8, 8, 6 |
Accept (Poster) |
212 |
7.33 |
ARTEMIS: Attention-based Retrieval with Text-Explicit Matching and Implicit Similarity |
8, 8, 6 |
Accept (Poster) |
213 |
7.33 |
Transition to Linearity of Wide Neural Networks is an Emerging Property of Assembling Weak Models |
8, 8, 6 |
Accept (Spotlight) |
214 |
7.33 |
Compositional Training for End-to-End Deep AUC Maximization |
6, 8, 8 |
Accept (Spotlight) |
215 |
7.33 |
Chunked Autoregressive GAN for Conditional Waveform Synthesis |
8, 8, 6 |
Accept (Poster) |
216 |
7.33 |
Critical Points in Quantum Generative Models |
8, 6, 8 |
Accept (Poster) |
217 |
7.33 |
Improving Mutual Information Estimation with Annealed and Energy-Based Bounds |
8, 6, 8 |
Accept (Poster) |
218 |
7.33 |
Constructing a Good Behavior Basis for Transfer using Generalized Policy Updates |
10, 6, 6 |
Accept (Poster) |
219 |
7.33 |
Fast topological clustering with Wasserstein distance |
6, 8, 8 |
Accept (Poster) |
220 |
7.33 |
Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis |
8, 6, 8 |
Accept (Poster) |
221 |
7.33 |
Distribution Compression in Near-Linear Time |
8, 8, 6 |
Accept (Poster) |
222 |
7.33 |
Learning-Augmented $k$-means Clustering |
8, 8, 6 |
Accept (Spotlight) |
223 |
7.33 |
CoBERL: Contrastive BERT for Reinforcement Learning |
8, 8, 6 |
Accept (Spotlight) |
224 |
7.33 |
Actor-critic is implicitly biased towards high entropy optimal policies |
6, 8, 8 |
Accept (Poster) |
225 |
7.33 |
Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness |
6, 8, 8 |
Accept (Poster) |
226 |
7.33 |
Controlling Directions Orthogonal to a Classifier |
6, 8, 8 |
Accept (Spotlight) |
227 |
7.33 |
GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation |
6, 8, 8 |
Accept (Oral) |
228 |
7.33 |
Boosting Randomized Smoothing with Variance Reduced Classifiers |
6, 8, 8 |
Accept (Spotlight) |
229 |
7.33 |
A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion |
8, 8, 6 |
Accept (Poster) |
230 |
7.33 |
Efficient Self-supervised Vision Transformers for Representation Learning |
8, 6, 8 |
Accept (Poster) |
231 |
7.33 |
Hybrid Random Features |
6, 8, 8 |
Accept (Poster) |
232 |
7.33 |
Relational Surrogate Loss Learning |
8, 6, 8 |
Accept (Poster) |
233 |
7.33 |
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation |
8, 8, 6 |
Accept (Poster) |
234 |
7.33 |
IntSGD: Adaptive Floatless Compression of Stochastic Gradients |
8, 8, 6 |
Accept (Spotlight) |
235 |
7.33 |
Causal ImageNet: How to discover spurious features in Deep Learning? |
8, 6, 8 |
Accept (Poster) |
236 |
7.33 |
ProtoRes: Proto-Residual Network for Pose Authoring via Learned Inverse Kinematics |
8, 8, 6 |
Accept (Oral) |
237 |
7.25 |
Learning Long-Term Reward Redistribution via Randomized Return Decomposition |
8, 8, 5, 8 |
Accept (Spotlight) |
238 |
7.25 |
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks |
5, 6, 8, 10 |
Accept (Poster) |
239 |
7.25 |
Self-supervised Learning is More Robust to Dataset Imbalance |
8, 8, 5, 8 |
Accept (Spotlight) |
240 |
7.25 |
Improving Federated Learning Face Recognition via Privacy-Agnostic Clusters |
8, 5, 8, 8 |
Accept (Spotlight) |
241 |
7.25 |
An Experimental Design Perspective on Exploration in Reinforcement Learning |
8, 8, 5, 8 |
Accept (Poster) |
242 |
7.25 |
Recycling Model Updates in Federated Learning: Are Gradient Subspaces Low-Rank? |
5, 8, 8, 8 |
Accept (Poster) |
243 |
7.25 |
Evaluation Metrics for Graph Generative Models: Problems, Pitfalls, and Practical Solutions |
5, 8, 8, 8 |
Accept (Spotlight) |
244 |
7.25 |
POETREE: Interpretable Policy Learning with Adaptive Decision Trees |
8, 8, 5, 8 |
Accept (Spotlight) |
245 |
7.25 |
Differentiable Scaffolding Tree for Molecule Optimization |
5, 8, 10, 6 |
Accept (Poster) |
246 |
7.25 |
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems |
8, 5, 8, 8 |
Accept (Spotlight) |
247 |
7.25 |
On the Generalization of Models Trained with SGD: Information-Theoretic Bounds and Implications |
8, 5, 6, 10 |
Accept (Poster) |
248 |
7.25 |
CLEVA-Compass: A Continual Learning Evaluation Assessment Compass to Promote Research Transparency and Comparability |
8, 8, 5, 8 |
Accept (Poster) |
249 |
7.25 |
On Predicting Generalization using GANs |
8, 8, 5, 8 |
Accept (Spotlight) |
250 |
7.25 |
Learning Optimal Conformal Classifiers |
8, 5, 8, 8 |
Accept (Spotlight) |
251 |
7.25 |
Fixed Neural Network Steganography: Train the images, not the network |
8, 8, 5, 8 |
Accept (Poster) |
252 |
7.25 |
Low-rank Matrix Recovery with Unknown Correspondence |
5, 10, 8, 6 |
Reject |
253 |
7.25 |
Hidden Convexity of Wasserstein GANs: Interpretable Generative Models with Closed-Form Solutions |
8, 8, 5, 8 |
Accept (Poster) |
254 |
7.25 |
Bridging the Gap: Providing Post-Hoc Symbolic Explanations for Sequential Decision-Making Problems with Inscrutable Representations |
10, 6, 8, 5 |
Accept (Poster) |
255 |
7.25 |
How Do Vision Transformers Work? |
8, 8, 5, 8 |
Accept (Spotlight) |
256 |
7.25 |
Graph-less Neural Networks: Teaching Old MLPs New Tricks Via Distillation |
3, 8, 10, 8 |
Accept (Poster) |
257 |
7.25 |
Continuously Discovering Novel Strategies via Reward-Switching Policy Optimization |
8, 8, 5, 8 |
Accept (Poster) |
258 |
7.25 |
Continual Learning with Recursive Gradient Optimization |
8, 8, 5, 8 |
Accept (Spotlight) |
259 |
7.2 |
Pix2seq: A Language Modeling Framework for Object Detection |
8, 6, 8, 6, 8 |
Accept (Poster) |
260 |
7.2 |
Responsible Disclosure of Generative Models Using Scalable Fingerprinting |
6, 8, 6, 8, 8 |
Accept (Spotlight) |
261 |
7.2 |
Dual Lottery Ticket Hypothesis |
6, 6, 8, 8, 8 |
Accept (Poster) |
262 |
7.2 |
SGD Can Converge to Local Maxima |
6, 8, 8, 6, 8 |
Accept (Spotlight) |
263 |
7.2 |
SPIRAL: Self-supervised Perturbation-Invariant Representation Learning for Speech Pre-Training |
8, 8, 8, 6, 6 |
Accept (Poster) |
264 |
7.2 |
Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration |
8, 8, 6, 6, 8 |
Accept (Spotlight) |
265 |
7.2 |
Fairness in Representation for Multilingual NLP: Insights from Controlled Experiments on Conditional Language Modeling |
8, 8, 8, 6, 6 |
Accept (Spotlight) |
266 |
7.2 |
MetaMorph: Learning Universal Controllers with Transformers |
8, 6, 6, 8, 8 |
Accept (Poster) |
267 |
7.2 |
Transformer-based Transform Coding |
8, 8, 6, 6, 8 |
Accept (Poster) |
268 |
7.2 |
Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions |
6, 8, 8, 8, 6 |
Accept (Spotlight) |
269 |
7 |
A Reduction-Based Framework for Conservative Bandits and Reinforcement Learning |
8, 6, 8, 6 |
Accept (Poster) |
270 |
7 |
Visual Correspondence Hallucination |
8, 5, 8 |
Accept (Poster) |
271 |
7 |
Online Hyperparameter Meta-Learning with Hypergradient Distillation |
6, 8, 8, 6 |
Accept (Spotlight) |
272 |
7 |
Flow-based Recurrent Belief State Learning for POMDPs |
6, 8, 6, 8 |
Reject |
273 |
7 |
Leveraging unlabeled data to predict out-of-distribution performance |
8, 5, 8, 8, 6 |
Accept (Poster) |
274 |
7 |
Contextualized Scene Imagination for Generative Commonsense Reasoning |
6, 6, 8, 8 |
Accept (Poster) |
275 |
7 |
Multi-scale Feature Learning Dynamics: Insights for Double Descent |
8, 8, 5 |
Reject |
276 |
7 |
Conditional Object-Centric Learning from Video |
6, 8, 6, 8 |
Accept (Poster) |
277 |
7 |
$\mathrm{SO}(2)$-Equivariant Reinforcement Learning |
8, 8, 8, 6, 5 |
Accept (Spotlight) |
278 |
7 |
Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations? |
8, 6, 6, 8 |
Accept (Poster) |
279 |
7 |
Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View |
6, 6, 8, 8 |
Accept (Poster) |
280 |
7 |
Message Passing Neural PDE Solvers |
8, 6, 6, 8 |
Accept (Spotlight) |
281 |
7 |
Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction |
6, 8, 6, 8 |
Accept (Poster) |
282 |
7 |
Analyzing and Improving the Optimization Landscape of Noise-Contrastive Estimation |
8, 6, 8, 6 |
Accept (Spotlight) |
283 |
7 |
Convergent Boosted Smoothing for Modeling GraphData with Tabular Node Features |
8, 8, 6, 6 |
Accept (Spotlight) |
284 |
7 |
Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations |
8, 8, 6, 6 |
Accept (Poster) |
285 |
7 |
Gradient Information Matters in Policy Optimization by Back-propagating through Model |
6, 8, 6, 8 |
Accept (Poster) |
286 |
7 |
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching |
8, 6, 8, 6 |
Accept (Poster) |
287 |
7 |
The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs |
8, 6, 6, 8 |
Accept (Poster) |
288 |
7 |
Efficient Active Search for Combinatorial Optimization Problems |
8, 8, 6, 6 |
Accept (Poster) |
289 |
7 |
Equivariant Transformers for Neural Network based Molecular Potentials |
6, 8, 6, 8 |
Accept (Spotlight) |
290 |
7 |
C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks |
6, 8, 8, 6 |
Accept (Poster) |
291 |
7 |
Self-Joint Supervised Learning |
8, 5, 8 |
Accept (Poster) |
292 |
7 |
CoordX: Accelerating Implicit Neural Representation with a Split MLP Architecture |
8, 6, 8, 6 |
Accept (Poster) |
293 |
7 |
COptiDICE: Offline Constrained Reinforcement Learning via Stationary Distribution Correction Estimation |
6, 8, 8, 6 |
Accept (Spotlight) |
294 |
7 |
Value Gradient weighted Model-Based Reinforcement Learning |
6, 8, 6, 8 |
Accept (Spotlight) |
295 |
7 |
Who Is Your Right Mixup Partner in Positive and Unlabeled Learning |
6, 8, 6, 8 |
Accept (Poster) |
296 |
7 |
Phase Collapse in Neural Networks |
8, 8, 6, 6 |
Accept (Poster) |
297 |
7 |
High Probability Generalization Bounds for Minimax Problems with Fast Rates |
8, 6, 8, 6 |
Accept (Poster) |
298 |
7 |
Fortuitous Forgetting in Connectionist Networks |
6, 6, 10, 6 |
Accept (Poster) |
299 |
7 |
When should agents explore? |
6, 8, 8, 6 |
Accept (Spotlight) |
300 |
7 |
Rethinking Adversarial Transferability from a Data Distribution Perspective |
5, 8, 8 |
Accept (Poster) |
301 |
7 |
Differentially Private Fractional Frequency Moments Estimation with Polylogarithmic Space |
8, 6, 8, 6 |
Accept (Poster) |
302 |
7 |
Compositional Attention: Disentangling Search and Retrieval |
8, 6, 6, 8 |
Accept (Spotlight) |
303 |
7 |
Stochastic Training is Not Necessary for Generalization |
6, 10, 8, 5, 6 |
Accept (Poster) |
304 |
7 |
Divisive Feature Normalization Improves Image Recognition Performance in AlexNet |
6, 8, 8, 6 |
Accept (Poster) |
305 |
7 |
MCMC Should Mix: Learning Energy-Based Model with Flow-Based Backbone |
8, 6, 6, 8 |
Accept (Poster) |
306 |
7 |
Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning |
8, 8, 6, 6 |
Accept (Spotlight) |
307 |
7 |
Minimax Optimization with Smooth Algorithmic Adversaries |
8, 8, 6, 6 |
Accept (Poster) |
308 |
7 |
On Bridging Generic and Personalized Federated Learning for Image Classification |
5, 8, 8 |
Accept (Spotlight) |
309 |
7 |
Is High Variance Unavoidable in RL? A Case Study in Continuous Control |
6, 10, 6, 6 |
Accept (Poster) |
310 |
7 |
Chaos is a Ladder: A New Understanding of Contrastive Learning |
6, 8, 8, 6 |
Accept (Poster) |
311 |
7 |
Learning Hierarchical Structures with Differentiable Nondeterministic Stacks |
6, 8, 6, 8 |
Accept (Spotlight) |
312 |
7 |
Spanning Tree-based Graph Generation for Molecules |
6, 6, 8, 8 |
Accept (Spotlight) |
313 |
7 |
A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning |
6, 6, 8, 8 |
Accept (Poster) |
314 |
7 |
Domain Adversarial Training: A Game Perspective |
6, 8, 6, 8 |
Accept (Poster) |
315 |
7 |
Joint Shapley values: a measure of joint feature importance |
5, 8, 8 |
Accept (Poster) |
316 |
7 |
Learning Transferable Reward for Query Object Localization with Policy Adaptation |
8, 6, 6, 8 |
Accept (Poster) |
317 |
7 |
On Lottery Tickets and Minimal Task Representations in Deep Reinforcement Learning |
8, 5, 8 |
Accept (Spotlight) |
318 |
7 |
Coherence-based Label Propagation over Time Series for Accelerated Active Learning |
10, 6, 6, 6 |
Accept (Poster) |
319 |
7 |
Learning Towards The Largest Margins |
8, 6, 8, 6 |
Accept (Poster) |
320 |
7 |
Energy-Based Learning for Cooperative Games, with Applications to Valuation Problems in Machine Learning |
6, 8, 8, 6 |
Accept (Poster) |
321 |
7 |
Efficient and Modular Implicit Differentiation |
10, 3, 8 |
Reject |
322 |
7 |
Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path |
6, 6, 8, 8 |
Accept (Oral) |
323 |
7 |
Contrastive Fine-grained Class Clustering via Generative Adversarial Networks |
8, 6, 8, 6 |
Accept (Spotlight) |
324 |
7 |
The MultiBERTs: BERT Reproductions for Robustness Analysis |
6, 8, 8, 6 |
Accept (Spotlight) |
325 |
7 |
Noisy Feature Mixup |
6, 8, 6, 8 |
Accept (Poster) |
326 |
7 |
Geometric and Physical Quantities improve E(3) Equivariant Message Passing |
6, 6, 6, 8, 6, 10 |
Accept (Spotlight) |
327 |
7 |
Pyraformer: Low-Complexity Pyramidal Attention for Long-Range Time Series Modeling and Forecasting |
8, 6, 6, 8 |
Accept (Oral) |
328 |
7 |
NODE-GAM: Neural Generalized Additive Model for Interpretable Deep Learning |
8, 5, 8 |
Accept (Spotlight) |
329 |
7 |
MonoDistill: Learning Spatial Features for Monocular 3D Object Detection |
8, 6, 8, 8, 5 |
Accept (Poster) |
330 |
7 |
Multi-objective Optimization by Learning Space Partition |
8, 8, 6, 6 |
Accept (Poster) |
331 |
7 |
Should I Run Offline Reinforcement Learning or Behavioral Cloning? |
6, 8, 6, 8 |
Accept (Poster) |
332 |
7 |
Bootstrapping Semantic Segmentation with Regional Contrast |
8, 8, 6, 6 |
Accept (Poster) |
333 |
7 |
Long Expressive Memory for Sequence Modeling |
8, 8, 6, 6 |
Accept (Spotlight) |
334 |
7 |
D-CODE: Discovering Closed-form ODEs from Observed Trajectories |
8, 6, 8, 6 |
Accept (Spotlight) |
335 |
7 |
Generalization of Overparametrized Deep Neural Network Under Noisy Observations |
8, 8, 6, 6 |
Accept (Poster) |
336 |
7 |
A generalization of the randomized singular value decomposition |
8, 8, 5 |
Accept (Poster) |
337 |
7 |
Anomaly Detection for Tabular Data with Internal Contrastive Learning |
6, 8, 8, 6 |
Accept (Poster) |
338 |
7 |
Churn Reduction via Distillation |
5, 8, 8 |
Accept (Spotlight) |
339 |
7 |
Spherical Message Passing for 3D Molecular Graphs |
5, 8, 8 |
Accept (Poster) |
340 |
7 |
Learned Simulators for Turbulence |
8, 6, 6, 8 |
Accept (Poster) |
341 |
7 |
Active Hierarchical Exploration with Stable Subgoal Representation Learning |
6, 8, 6, 8 |
Accept (Poster) |
342 |
7 |
Procedural generalization by planning with self-supervised world models |
8, 8, 6, 6 |
Accept (Poster) |
343 |
7 |
You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks |
8, 6, 8, 6 |
Accept (Poster) |
344 |
7 |
On the Limitations of Multimodal VAEs |
8, 6, 8, 6 |
Accept (Poster) |
345 |
7 |
DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization |
8, 6, 6, 8 |
Accept (Spotlight) |
346 |
7 |
LoRA: Low-Rank Adaptation of Large Language Models |
6, 8, 6, 8 |
Accept (Poster) |
347 |
7 |
Multi-Stage Episodic Control for Strategic Exploration in Text Games |
8, 6, 8, 6 |
Accept (Spotlight) |
348 |
7 |
Unsupervised Discovery of Object Radiance Fields |
5, 8, 8 |
Accept (Poster) |
349 |
7 |
Machine Learning For Elliptic PDEs: Fast Rate Generalization Bound, Neural Scaling Law and Minimax Optimality |
8, 6, 8, 6 |
Accept (Poster) |
350 |
7 |
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness? |
8, 8, 6, 6 |
Accept (Poster) |
351 |
7 |
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations |
8, 6, 8, 8, 5 |
Accept (Spotlight) |
352 |
7 |
DP-REC: Private & Communication-Efficient Federated Learning |
6, 8, 8, 6 |
Reject |
353 |
7 |
Context-Aware Sparse Deep Coordination Graphs |
8, 6, 6, 8 |
Accept (Spotlight) |
354 |
7 |
Sqrt(d) Dimension Dependence of Langevin Monte Carlo |
6, 8, 6, 8 |
Accept (Poster) |
355 |
7 |
Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling |
6, 6, 8, 8 |
Accept (Poster) |
356 |
7 |
Filling the G_ap_s: Multivariate Time Series Imputation by Graph Neural Networks |
8, 8, 6, 6 |
Accept (Poster) |
357 |
7 |
Resolving Training Biases via Influence-based Data Relabeling |
8, 8, 6, 6 |
Accept (Oral) |
358 |
7 |
Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100 |
8, 6, 6, 8 |
Accept (Spotlight) |
359 |
7 |
Shuffle Private Stochastic Convex Optimization |
6, 8, 8, 6 |
Accept (Poster) |
360 |
7 |
PF-GNN: Differentiable particle filtering based approximation of universal graph representations |
8, 6, 8, 6 |
Accept (Poster) |
361 |
7 |
Distributionally Robust Models with Parametric Likelihood Ratios |
6, 8, 6, 8 |
Accept (Poster) |
362 |
7 |
Random matrices in service of ML footprint: ternary random features with no performance loss |
8, 8, 6, 6 |
Accept (Poster) |
363 |
7 |
Equivariant Subgraph Aggregation Networks |
6, 8, 8, 6 |
Accept (Spotlight) |
364 |
7 |
Sample and Computation Redistribution for Efficient Face Detection |
6, 8, 8, 6 |
Accept (Poster) |
365 |
7 |
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis |
6, 6, 8, 8 |
Accept (Poster) |
366 |
7 |
Differentiable Prompt Makes Pre-trained Language Models Better Few-shot Learners |
8, 6, 6, 8 |
Accept (Poster) |
367 |
7 |
Chemical-Reaction-Aware Molecule Representation Learning |
8, 8, 6, 6 |
Accept (Poster) |
368 |
7 |
CURVATURE-GUIDED DYNAMIC SCALE NETWORKS FOR MULTI-VIEW STEREO |
6, 8, 8, 6 |
Accept (Poster) |
369 |
7 |
Phenomenology of Double Descent in Finite-Width Neural Networks |
8, 8, 8, 8, 3 |
Accept (Poster) |
370 |
7 |
NASPY: Automated Extraction of Automated Machine Learning Models |
6, 8, 8, 6 |
Accept (Spotlight) |
371 |
7 |
Hindsight: Posterior-guided training of retrievers for improved open-ended generation |
8, 6, 8, 6 |
Accept (Poster) |
372 |
7 |
Revisiting Over-smoothing in BERT from the Perspective of Graph |
6, 6, 8, 8 |
Accept (Spotlight) |
373 |
7 |
Permutation-Based SGD: Is Random Optimal? |
10, 6, 6, 6 |
Accept (Poster) |
374 |
7 |
Scarf: Self-Supervised Contrastive Learning using Random Feature Corruption |
6, 6, 8, 8 |
Accept (Spotlight) |
375 |
7 |
An Unconstrained Layer-Peeled Perspective on Neural Collapse |
6, 6, 8, 8 |
Accept (Poster) |
376 |
7 |
Data-Driven Offline Optimization for Architecting Hardware Accelerators |
6, 6, 8, 8 |
Accept (Poster) |
377 |
7 |
cosFormer: Rethinking Softmax In Attention |
8, 6, 8, 6 |
Accept (Poster) |
378 |
7 |
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks |
8, 8, 6, 6 |
Reject |
379 |
7 |
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series |
8, 6, 8, 6 |
Accept (Spotlight) |
380 |
7 |
The Role of Permutation Invariance in Linear Mode Connectivity of Neural Networks |
8, 8, 6, 6 |
Accept (Poster) |
381 |
7 |
Variational methods for simulation-based inference |
6, 8, 6, 8 |
Accept (Spotlight) |
382 |
7 |
EE-Net: Exploitation-Exploration Neural Networks in Contextual Bandits |
6, 6, 8, 8 |
Accept (Spotlight) |
383 |
7 |
Ancestral protein sequence reconstruction using a tree-structured Ornstein-Uhlenbeck variational autoencoder |
8, 5, 8 |
Accept (Poster) |
384 |
7 |
On the Uncomputability of Partition Functions in Energy-Based Sequence Models |
6, 8, 6, 8 |
Accept (Spotlight) |
385 |
7 |
GiraffeDet: A Heavy-Neck Paradigm for Object Detection |
8, 5, 8 |
Accept (Poster) |
386 |
7 |
On Distributed Adaptive Optimization with Gradient Compression |
8, 8, 5 |
Accept (Poster) |
387 |
7 |
Unsupervised Semantic Segmentation by Distilling Feature Correspondences |
8, 6, 8, 6 |
Accept (Poster) |
388 |
7 |
Deep ReLU Networks Preserve Expected Length |
8, 6, 6, 8 |
Accept (Poster) |
389 |
7 |
Neural Relational Inference with Node-Specific Information |
8, 5, 8 |
Accept (Poster) |
390 |
7 |
GreaseLM: Graph REASoning Enhanced Language Models |
8, 8, 6, 6 |
Accept (Spotlight) |
391 |
6.83 |
Offline Reinforcement Learning with Value-based Episodic Memory |
8, 8, 5, 6, 8, 6 |
Accept (Poster) |
392 |
6.8 |
Multi-Critic Actor Learning: Teaching RL Policies to Act with Style |
6, 8, 6, 6, 8 |
Accept (Poster) |
393 |
6.8 |
Learning to Generalize across Domains on Single Test Samples |
8, 5, 8, 8, 5 |
Accept (Poster) |
394 |
6.8 |
Reinforcement Learning in Presence of Discrete Markovian Context Evolution |
8, 8, 6, 6, 6 |
Accept (Poster) |
395 |
6.8 |
Finite-Time Convergence and Sample Complexity of Multi-Agent Actor-Critic Reinforcement Learning with Average Reward |
6, 8, 8, 6, 6 |
Accept (Spotlight) |
396 |
6.8 |
How Does SimSiam Avoid Collapse Without Negative Samples? Towards a Unified Understanding of Progress in SSL |
8, 6, 6, 6, 8 |
Accept (Poster) |
397 |
6.8 |
Sharp Learning Bounds for Contrastive Unsupervised Representation Learning |
6, 8, 6, 8, 6 |
Reject |
398 |
6.8 |
Revisiting Design Choices in Offline Model Based Reinforcement Learning |
6, 6, 8, 6, 8 |
Accept (Spotlight) |
399 |
6.8 |
Learning Altruistic Behaviours in Reinforcement Learning without External Rewards |
6, 6, 8, 6, 8 |
Accept (Spotlight) |
400 |
6.8 |
Latent Image Animator: Learning to animate image via latent space navigation |
8, 6, 6, 6, 8 |
Accept (Poster) |
401 |
6.8 |
On the Certified Robustness for Ensemble Models and Beyond |
8, 6, 6, 8, 6 |
Accept (Poster) |
402 |
6.8 |
Tracking the risk of a deployed model and detecting harmful distribution shifts |
8, 6, 6, 8, 6 |
Accept (Poster) |
403 |
6.8 |
Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks |
6, 6, 6, 8, 8 |
Accept (Poster) |
404 |
6.75 |
Adversarially Robust Conformal Prediction |
8, 6, 8, 5 |
Accept (Poster) |
405 |
6.75 |
Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations |
6, 5, 8, 8 |
Accept (Poster) |
406 |
6.75 |
Pareto Policy Pool for Model-based Offline Reinforcement Learning |
8, 5, 6, 8 |
Accept (Poster) |
407 |
6.75 |
Global Convergence of Multi-Agent Policy Gradient in Markov Potential Games |
6, 8, 5, 8 |
Accept (Poster) |
408 |
6.75 |
FALCON: Fast Visual Concept Learning by Integrating Images, Linguistic descriptions, and Conceptual Relations |
5, 8, 8, 6 |
Accept (Poster) |
409 |
6.75 |
Multiset-Equivariant Set Prediction with Approximate Implicit Differentiation |
5, 8, 6, 8 |
Accept (Poster) |
410 |
6.75 |
Deep AutoAugment |
6, 8, 8, 5 |
Accept (Poster) |
411 |
6.75 |
Surreal-GAN:Semi-Supervised Representation Learning via GAN for uncovering heterogeneous disease-related imaging patterns |
8, 5, 8, 6 |
Accept (Poster) |
412 |
6.75 |
miniF2F: a cross-system benchmark for formal Olympiad-level mathematics |
6, 8, 5, 8 |
Accept (Poster) |
413 |
6.75 |
Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields |
5, 6, 6, 10 |
Accept (Poster) |
414 |
6.75 |
Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity |
8, 5, 8, 6 |
Accept (Poster) |
415 |
6.75 |
Mapping Language Models to Grounded Conceptual Spaces |
6, 8, 8, 5 |
Accept (Poster) |
416 |
6.75 |
How to Train Your MAML to Excel in Few-Shot Classification |
3, 8, 8, 8 |
Accept (Poster) |
417 |
6.75 |
BAM: Bayes Augmented with Memory |
8, 8, 5, 6 |
Accept (Poster) |
418 |
6.75 |
Learning Object-Oriented Dynamics for Planning from Text |
6, 5, 8, 8 |
Accept (Poster) |
419 |
6.75 |
Enhancing Cross-lingual Transfer by Manifold Mixup |
8, 5, 6, 8 |
Accept (Poster) |
420 |
6.75 |
SketchODE: Learning neural sketch representation in continuous time |
6, 8, 8, 5 |
Accept (Poster) |
421 |
6.75 |
Constrained Graph Mechanics Networks |
8, 5, 8, 6 |
Accept (Poster) |
422 |
6.75 |
Generalized rectifier wavelet covariance models for texture synthesis |
3, 8, 8, 8 |
Accept (Poster) |
423 |
6.75 |
Improving Non-Autoregressive Translation Models Without Distillation |
8, 8, 8, 3 |
Accept (Poster) |
424 |
6.75 |
Path Integral Sampler: A Stochastic Control Approach For Sampling |
5, 6, 8, 8 |
Accept (Poster) |
425 |
6.75 |
Adversarial Support Alignment |
8, 8, 3, 8 |
Accept (Spotlight) |
426 |
6.75 |
NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs |
8, 5, 8, 6 |
Accept (Poster) |
427 |
6.75 |
Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design |
8, 8, 8, 3 |
Accept (Spotlight) |
428 |
6.75 |
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training |
8, 6, 5, 8 |
Accept (Poster) |
429 |
6.75 |
Better Supervisory Signals by Observing Learning Paths |
8, 6, 5, 8 |
Accept (Poster) |
430 |
6.75 |
A First-Occupancy Representation for Reinforcement Learning |
6, 5, 8, 8 |
Accept (Poster) |
431 |
6.75 |
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training |
5, 8, 8, 6 |
Accept (Poster) |
432 |
6.75 |
Knowledge Removal in Sampling-based Bayesian Inference |
8, 8, 3, 8 |
Accept (Poster) |
433 |
6.75 |
Leveraging Automated Unit Tests for Unsupervised Code Translation |
6, 5, 8, 8 |
Accept (Spotlight) |
434 |
6.75 |
Synchromesh: Reliable Code Generation from Pre-trained Language Models |
8, 8, 5, 6 |
Accept (Poster) |
435 |
6.75 |
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation |
6, 8, 8, 5 |
Accept (Poster) |
436 |
6.75 |
Learning Neural Contextual Bandits through Perturbed Rewards |
6, 5, 8, 8 |
Accept (Poster) |
437 |
6.75 |
Proving the Lottery Ticket Hypothesis for Convolutional Neural Networks |
6, 8, 5, 8 |
Accept (Poster) |
438 |
6.75 |
Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs |
6, 8, 8, 5 |
Accept (Poster) |
439 |
6.75 |
Towards Unknown-aware Learning with Virtual Outlier Synthesis |
5, 8, 8, 6 |
Accept (Poster) |
440 |
6.75 |
Unrolling PALM for Sparse Semi-Blind Source Separation |
6, 5, 8, 8 |
Accept (Poster) |
441 |
6.75 |
Lottery Tickets can have Structural Sparsity |
6, 8, 5, 8 |
Reject |
442 |
6.75 |
Exploring Memorization in Adversarial Training |
6, 3, 8, 10 |
Accept (Poster) |
443 |
6.75 |
Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning |
5, 6, 8, 8 |
Accept (Poster) |
444 |
6.75 |
Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game |
5, 8, 6, 8 |
Accept (Poster) |
445 |
6.75 |
Learning to Complete Code with Sketches |
8, 5, 6, 8 |
Accept (Poster) |
446 |
6.75 |
GNN is a Counter? Revisiting GNN for Question Answering |
8, 8, 5, 6 |
Accept (Poster) |
447 |
6.75 |
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning |
8, 8, 6, 5 |
Reject |
448 |
6.75 |
On the Learning of Quasimetrics |
8, 5, 6, 8 |
Accept (Poster) |
449 |
6.75 |
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios |
8, 5, 6, 8 |
Accept (Poster) |
450 |
6.75 |
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect |
8, 5, 6, 8 |
Accept (Poster) |
451 |
6.75 |
Implicit Bias of Projected Subgradient Method Gives Provable Robust Recovery of Subspaces of Unknown Codimension |
8, 5, 6, 8 |
Accept (Spotlight) |
452 |
6.75 |
A Fine-Tuning Approach to Belief State Modeling |
3, 8, 8, 8 |
Accept (Poster) |
453 |
6.75 |
ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning |
8, 5, 6, 8 |
Accept (Poster) |
454 |
6.75 |
Learning Efficient Image Super-Resolution Networks via Structure-Regularized Pruning |
5, 8, 6, 8 |
Accept (Poster) |
455 |
6.75 |
Learning to Remember Patterns: Pattern Matching Memory Networks for Traffic Forecasting |
8, 8, 6, 5 |
Accept (Poster) |
456 |
6.75 |
Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently |
8, 6, 8, 5 |
Accept (Poster) |
457 |
6.75 |
Dynamics-Aware Comparison of Learned Reward Functions |
6, 8, 5, 8 |
Accept (Spotlight) |
458 |
6.75 |
Scene Transformer: A unified architecture for predicting future trajectories of multiple agents |
8, 5, 6, 8 |
Accept (Poster) |
459 |
6.75 |
Model-augmented Prioritized Experience Replay |
8, 5, 8, 6 |
Accept (Poster) |
460 |
6.75 |
Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory |
8, 5, 8, 6 |
Accept (Poster) |
461 |
6.75 |
Topological Experience Replay |
5, 8, 6, 8 |
Accept (Poster) |
462 |
6.75 |
A Loss Curvature Perspective on Training Instabilities of Deep Learning Models |
5, 8, 8, 6 |
Accept (Poster) |
463 |
6.75 |
Representation Learning for Online and Offline RL in Low-rank MDPs |
8, 6, 5, 8 |
Accept (Spotlight) |
464 |
6.75 |
DIVA: Dataset Derivative of a Learning Task |
5, 8, 8, 6 |
Accept (Poster) |
465 |
6.75 |
Sound and Complete Neural Network Repair with Minimality and Locality Guarantees |
8, 6, 8, 5 |
Accept (Poster) |
466 |
6.67 |
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations |
6, 8, 6 |
Accept (Poster) |
467 |
6.67 |
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework |
6, 6, 8 |
Accept (Poster) |
468 |
6.67 |
Invariant Causal Representation Learning for Out-of-Distribution Generalization |
8, 6, 6 |
Accept (Poster) |
469 |
6.67 |
Trainable Learning Rate |
5, 3, 8, 6, 8, 10 |
Reject |
470 |
6.67 |
AQUILA: Communication Efficient Federated Learning with Adaptive Quantization of Lazily-Aggregated Gradients |
6, 8, 6 |
Reject |
471 |
6.67 |
End-to-End Learning of Probabilistic Hierarchies on Graphs |
6, 8, 6 |
Accept (Poster) |
472 |
6.67 |
TRAIL: Near-Optimal Imitation Learning with Suboptimal Data |
6, 8, 6 |
Accept (Poster) |
473 |
6.67 |
Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators |
6, 8, 6 |
Accept (Poster) |
474 |
6.67 |
GradSign: Model Performance Inference with Theoretical Insights |
6, 8, 6 |
Accept (Poster) |
475 |
6.67 |
Practical Conditional Neural Process Via Tractable Dependent Predictions |
8, 6, 6 |
Accept (Poster) |
476 |
6.67 |
PEARL: Data Synthesis via Private Embeddings and Adversarial Reconstruction Learning |
8, 6, 6 |
Accept (Poster) |
477 |
6.67 |
Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks |
8, 6, 6 |
Accept (Poster) |
478 |
6.67 |
Multimeasurement Generative Models |
6, 6, 8 |
Accept (Poster) |
479 |
6.67 |
Optimal Transport for Causal Discovery |
6, 8, 6 |
Accept (Spotlight) |
480 |
6.67 |
Uncertainty Modeling for Out-of-Distribution Generalization |
6, 8, 6 |
Accept (Poster) |
481 |
6.67 |
Neural Variational Dropout Processes |
6, 8, 6 |
Accept (Poster) |
482 |
6.67 |
Beyond ImageNet Attack: Towards Crafting Adversarial Examples for Black-box Domains |
8, 6, 6 |
Accept (Poster) |
483 |
6.67 |
X-model: Improving Data Efficiency in Deep Learning with A Minimax Model |
6, 6, 8 |
Accept (Poster) |
484 |
6.67 |
Zero Pixel Directional Boundary by Vector Transform |
8, 6, 6 |
Accept (Poster) |
485 |
6.67 |
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs |
6, 6, 8 |
Accept (Poster) |
486 |
6.67 |
Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification |
8, 6, 6 |
Accept (Poster) |
487 |
6.67 |
Inverse Online Learning: Understanding Non-Stationary and Reactionary Policies |
6, 8, 6 |
Accept (Poster) |
488 |
6.67 |
Reverse Engineering of Imperceptible Adversarial Image Perturbations |
6, 8, 6 |
Accept (Poster) |
489 |
6.67 |
Looking Back on Learned Experiences For Class/task Incremental Learning |
6, 8, 6 |
Accept (Spotlight) |
490 |
6.67 |
Safe Neurosymbolic Learning with Differentiable Symbolic Execution |
6, 8, 6 |
Accept (Poster) |
491 |
6.67 |
Towards Understanding the Robustness Against Evasion Attack on Categorical Data |
6, 8, 6 |
Accept (Poster) |
492 |
6.67 |
Hybrid Memoised Wake-Sleep: Approximate Inference at the Discrete-Continuous Interface |
6, 8, 6 |
Accept (Poster) |
493 |
6.67 |
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models |
6, 6, 8 |
Accept (Poster) |
494 |
6.67 |
Image BERT Pre-training with Online Tokenizer |
8, 6, 6 |
Accept (Poster) |
495 |
6.67 |
Automatic Loss Function Search for Predict-Then-Optimize Problems with Strong Ranking Property |
6, 8, 6 |
Accept (Poster) |
496 |
6.67 |
Learning Versatile Neural Architectures by Propagating Network Codes |
8, 6, 6 |
Accept (Poster) |
497 |
6.67 |
Sequence Approximation using Feedforward Spiking Neural Network for Spatiotemporal Learning: Theory and Optimization Methods |
8, 6, 6 |
Accept (Poster) |
498 |
6.67 |
Toward Faithful Case-based Reasoning through Learning Prototypes in a Nearest Neighbor-friendly Space. |
6, 8, 6 |
Accept (Poster) |
499 |
6.67 |
Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction |
6, 6, 8 |
Accept (Poster) |
500 |
6.67 |
When, Why, and Which Pretrained GANs Are Useful? |
6, 6, 8 |
Accept (Poster) |
501 |
6.67 |
Triangle and Four Cycle Counting with Predictions in Graph Streams |
6, 8, 6 |
Accept (Poster) |
502 |
6.67 |
Steerable Partial Differential Operators for Equivariant Neural Networks |
6, 8, 6 |
Accept (Poster) |
503 |
6.67 |
VC dimension of partially quantized neural networks in the overparametrized regime |
8, 6, 6 |
Accept (Poster) |
504 |
6.67 |
On Non-Random Missing Labels in Semi-Supervised Learning |
8, 6, 6 |
Accept (Poster) |
505 |
6.67 |
Provably Robust Adversarial Examples |
8, 6, 6 |
Accept (Poster) |
506 |
6.67 |
Dive Deeper Into Integral Pose Regression |
8, 6, 6 |
Accept (Poster) |
507 |
6.67 |
Properties from mechanisms: an equivariance perspective on identifiable representation learning |
6, 8, 6 |
Accept (Spotlight) |
508 |
6.67 |
Temporal Alignment Prediction for Supervised Representation Learning and Few-Shot Sequence Classification |
6, 8, 6 |
Accept (Poster) |
509 |
6.67 |
Online Facility Location with Predictions |
8, 6, 8, 6, 6, 6 |
Accept (Poster) |
510 |
6.67 |
BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis |
6, 6, 8 |
Accept (Poster) |
511 |
6.67 |
Privacy Implications of Shuffling |
6, 6, 8 |
Accept (Poster) |
512 |
6.67 |
High Probability Bounds for a Class of Nonconvex Algorithms with AdaGrad Stepsize |
6, 6, 8 |
Accept (Poster) |
513 |
6.67 |
Half-Inverse Gradients for Physical Deep Learning |
6, 8, 6 |
Accept (Spotlight) |
514 |
6.67 |
SimVLM: Simple Visual Language Model Pretraining with Weak Supervision |
6, 8, 6 |
Accept (Poster) |
515 |
6.67 |
Label Leakage and Protection in Two-party Split Learning |
8, 6, 6 |
Accept (Poster) |
516 |
6.67 |
RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning |
6, 8, 6 |
Accept (Poster) |
517 |
6.67 |
NETWORK INSENSITIVITY TO PARAMETER NOISE VIA PARAMETER ATTACK DURING TRAINING |
6, 8, 6 |
Accept (Poster) |
518 |
6.67 |
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program |
6, 8, 6 |
Accept (Poster) |
519 |
6.67 |
Information Bottleneck: Exact Analysis of (Quantized) Neural Networks |
6, 8, 6 |
Accept (Poster) |
520 |
6.67 |
DIVERSIFY to Generalize: Learning Generalized Representations for Time Series Classification |
8, 6, 6 |
Reject |
521 |
6.67 |
A Class of Short-term Recurrence Anderson Mixing Methods and Their Applications |
6, 6, 8 |
Accept (Poster) |
522 |
6.67 |
Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery |
8, 6, 6 |
Accept (Poster) |
523 |
6.67 |
Entroformer: A Transformer-based Entropy Model for Learned Image Compression |
6, 6, 8 |
Accept (Poster) |
524 |
6.67 |
Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph |
8, 6, 6 |
Accept (Poster) |
525 |
6.6 |
Revisiting Out-of-Distribution Detection: A Simple Baseline is Surprisingly Effective |
6, 3, 6, 10, 8 |
Reject |
526 |
6.6 |
P-Adapters: Robustly Extracting Factual Information from Language Models with Diverse Prompts |
8, 6, 5, 8, 6 |
Accept (Poster) |
527 |
6.6 |
Hierarchical Modular Framework for Long Horizon Instruction Following |
6, 3, 8, 8, 8 |
Reject |
528 |
6.6 |
Towards Better Understanding and Better Generalization of Low-shot Classification in Histology Images with Contrastive Learning |
6, 5, 8, 8, 6 |
Accept (Poster) |
529 |
6.6 |
Transformer with a Mixture of Gaussian Keys |
8, 5, 8, 6, 6 |
Reject |
530 |
6.6 |
A Unified Wasserstein Distributional Robustness Framework for Adversarial Training |
8, 5, 8, 6, 6 |
Accept (Poster) |
531 |
6.6 |
Learning meta-features for AutoML |
5, 6, 8, 6, 8 |
Accept (Spotlight) |
532 |
6.6 |
Sample Selection with Uncertainty of Losses for Learning with Noisy Labels |
5, 8, 6, 8, 6 |
Accept (Poster) |
533 |
6.5 |
From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness |
6, 8, 6, 6 |
Accept (Poster) |
534 |
6.5 |
Eigencurve: Optimal Learning Rate Schedule for SGD on Quadratic Objectives with Skewed Hessian Spectrums |
6, 6, 6, 8 |
Accept (Poster) |
535 |
6.5 |
Understanding the Variance Collapse of SVGD in High Dimensions |
8, 6, 6, 6 |
Accept (Poster) |
536 |
6.5 |
Optimizing Neural Networks with Gradient Lexicase Selection |
8, 6, 6, 6 |
Accept (Poster) |
537 |
6.5 |
Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views? |
6, 8, 6, 6 |
Accept (Poster) |
538 |
6.5 |
Map Induction: Compositional spatial submap learning for efficient exploration in novel environments |
6, 6, 8, 6 |
Accept (Poster) |
539 |
6.5 |
Efficient Computation of Deep Nonlinear Infinite-Width Neural Networks that Learn Features |
6, 8, 6, 6 |
Accept (Poster) |
540 |
6.5 |
Bag of Instances Aggregation Boosts Self-supervised Distillation |
8, 6, 6, 6 |
Accept (Poster) |
541 |
6.5 |
Confidence Adaptive Anytime Pixel-Level Recognition |
8, 6, 6, 6 |
Accept (Poster) |
542 |
6.5 |
Dynamic Least-Squares Regression |
6, 8, 6, 6 |
Reject |
543 |
6.5 |
Online Ad Hoc Teamwork under Partial Observability |
6, 6, 6, 8 |
Accept (Poster) |
544 |
6.5 |
On the Existence of Universal Lottery Tickets |
6, 8, 6, 6 |
Accept (Poster) |
545 |
6.5 |
Low-Budget Active Learning via Wasserstein Distance: An Integer Programming Approach |
6, 8, 6, 6 |
Accept (Poster) |
546 |
6.5 |
Understanding and Improving Graph Injection Attack by Promoting Unnoticeability |
6, 8, 6, 6 |
Accept (Poster) |
547 |
6.5 |
Predicting Physics in Mesh-reduced Space with Temporal Attention |
8, 6, 6, 6 |
Accept (Poster) |
548 |
6.5 |
On Incorporating Inductive Biases into VAEs |
8, 6, 6, 6 |
Accept (Poster) |
549 |
6.5 |
Gradient Importance Learning for Incomplete Observations |
8, 6, 6, 6 |
Accept (Poster) |
550 |
6.5 |
EigenGame Unloaded: When playing games is better than optimizing |
5, 8, 5, 8 |
Accept (Poster) |
551 |
6.5 |
Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning |
6, 8, 6, 6 |
Accept (Poster) |
552 |
6.5 |
Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps |
6, 8, 6, 6 |
Accept (Poster) |
553 |
6.5 |
Prototypical Contrastive Predictive Coding |
6, 8, 6, 6 |
Accept (Poster) |
554 |
6.5 |
Surrogate Gap Minimization Improves Sharpness-Aware Training |
6, 6, 8, 6 |
Accept (Poster) |
555 |
6.5 |
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions |
6, 8, 6, 6 |
Accept (Poster) |
556 |
6.5 |
Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization |
6, 6, 6, 8 |
Accept (Poster) |
557 |
6.5 |
Modular Lifelong Reinforcement Learning via Neural Composition |
6, 6, 6, 8 |
Accept (Poster) |
558 |
6.5 |
NASI: Label- and Data-agnostic Neural Architecture Search at Initialization |
6, 6, 6, 8 |
Accept (Poster) |
559 |
6.5 |
Objects in Semantic Topology |
8, 5, 5, 8 |
Accept (Poster) |
560 |
6.5 |
Policy Gradients Incorporating the Future |
8, 6, 6, 6 |
Accept (Poster) |
561 |
6.5 |
Effective Model Sparsification by Scheduled Grow-and-Prune Methods |
6, 6, 6, 8 |
Accept (Poster) |
562 |
6.5 |
Interacting Contour Stochastic Gradient Langevin Dynamics |
8, 6, 6, 6 |
Accept (Poster) |
563 |
6.5 |
DFSSATTEN: Dynamic Fine-grained Structured Sparse Attention Mechanism |
5, 5, 8, 8 |
Reject |
564 |
6.5 |
Bi-linear Value Networks for Multi-goal Reinforcement Learning |
6, 6, 6, 8 |
Accept (Poster) |
565 |
6.5 |
Cross-Domain Imitation Learning via Optimal Transport |
6, 6, 6, 8 |
Accept (Poster) |
566 |
6.5 |
Proof Artifact Co-Training for Theorem Proving with Language Models |
8, 5, 8, 5 |
Accept (Poster) |
567 |
6.5 |
A Program to Build E(N)-Equivariant Steerable CNNs |
8, 6, 6, 6 |
Accept (Poster) |
568 |
6.5 |
Differentially Private Fine-tuning of Language Models |
6, 8, 6, 6 |
Accept (Poster) |
569 |
6.5 |
DeSKO: Stability-Assured Robust Control with a Deep Stochastic Koopman Operator |
6, 8, 6, 6 |
Accept (Poster) |
570 |
6.5 |
How many degrees of freedom do we need to train deep networks: a loss landscape perspective |
6, 8, 6, 6 |
Accept (Poster) |
571 |
6.5 |
Learning Temporally Latent Causal Processes from General Temporal Data |
6, 6, 6, 8 |
Accept (Poster) |
572 |
6.5 |
Optimizing Few-Step Diffusion Samplers by Gradient Descent |
6, 8, 6, 6 |
Accept (Poster) |
573 |
6.5 |
Anisotropic Random Feature Regression in High Dimensions |
6, 6, 8, 6 |
Accept (Poster) |
574 |
6.5 |
Lottery Image Prior |
6, 8, 6, 6 |
Reject |
575 |
6.5 |
Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators |
8, 3, 6, 6, 8, 8 |
Accept (Poster) |
576 |
6.5 |
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization |
6, 6, 6, 8 |
Accept (Poster) |
577 |
6.5 |
Evaluating Model-Based Planning and Planner Amortization for Continuous Control |
6, 6, 8, 6 |
Accept (Poster) |
578 |
6.5 |
Variational Predictive Routing with Nested Subjective Timescales |
6, 6, 6, 8 |
Accept (Poster) |
579 |
6.5 |
Differentiable Expectation-Maximization for Set Representation Learning |
6, 6, 6, 8 |
Accept (Poster) |
580 |
6.5 |
HTLM: Hyper-Text Pre-Training and Prompting of Language Models |
6, 8, 6, 6 |
Accept (Poster) |
581 |
6.5 |
Fast AdvProp |
8, 8, 5, 5 |
Accept (Poster) |
582 |
6.5 |
Tighter Sparse Approximation Bounds for ReLU Neural Networks |
6, 6, 8, 6 |
Accept (Spotlight) |
583 |
6.5 |
T-WaveNet: A Tree-Structured Wavelet Neural Network for Time Series Signal Analysis |
8, 6, 6, 6 |
Accept (Poster) |
584 |
6.5 |
Skill-based Meta-Reinforcement Learning |
6, 6, 8, 6 |
Accept (Poster) |
585 |
6.5 |
Effect of scale on catastrophic forgetting in neural networks |
5, 5, 8, 8 |
Accept (Poster) |
586 |
6.5 |
AdaAug: Learning Class- and Instance-adaptive Data Augmentation Policies |
6, 6, 8, 6 |
Accept (Poster) |
587 |
6.5 |
Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences |
8, 6, 6, 6 |
Accept (Poster) |
588 |
6.5 |
How unlabeled data improve generalization in self-training? A one-hidden-layer theoretical analysis |
6, 6, 6, 8 |
Accept (Poster) |
589 |
6.5 |
Learning to Annotate Part Segmentation with Gradient Matching |
6, 8, 6, 6 |
Accept (Poster) |
590 |
6.5 |
Huber Additive Models for Non-stationary Time Series Analysis |
8, 6, 6, 6 |
Accept (Poster) |
591 |
6.5 |
Explaining Point Processes by Learning Interpretable Temporal Logic Rules |
6, 8, 6, 6 |
Accept (Poster) |
592 |
6.5 |
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits |
8, 6, 6, 6 |
Accept (Poster) |
593 |
6.5 |
Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off |
6, 6, 8, 6 |
Accept (Poster) |
594 |
6.5 |
Implicit Bias of Adversarial Training for Deep Neural Networks |
5, 8, 5, 8 |
Accept (Poster) |
595 |
6.5 |
Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations |
6, 8, 6, 6 |
Accept (Poster) |
596 |
6.5 |
AlphaZero-based Proof Cost Network to Aid Game Solving |
5, 8, 8, 5 |
Accept (Poster) |
597 |
6.5 |
Boosted Curriculum Reinforcement Learning |
6, 8, 6, 6 |
Accept (Poster) |
598 |
6.5 |
Maximum n-times Coverage for Vaccine Design |
8, 6, 6, 6 |
Accept (Poster) |
599 |
6.5 |
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm |
6, 8, 6, 6 |
Accept (Poster) |
600 |
6.5 |
Unsupervised Pose-Aware Part Decomposition for 3D Articulated Objects |
8, 5, 8, 5 |
Reject |
601 |
6.5 |
GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification |
6, 6, 8, 6 |
Accept (Poster) |
602 |
6.5 |
FlexConv: Continuous Kernel Convolutions With Differentiable Kernel Sizes |
8, 6, 6, 6 |
Accept (Poster) |
603 |
6.5 |
Backdoor Defense via Decoupling the Training Process |
6, 6, 6, 8 |
Accept (Poster) |
604 |
6.5 |
Few-shot Learning via Dirichlet Tessellation Ensemble |
6, 8, 6, 6 |
Accept (Poster) |
605 |
6.5 |
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different |
6, 6, 6, 8 |
Accept (Poster) |
606 |
6.5 |
Bayesian Framework for Gradient Leakage |
6, 8, 6, 6 |
Accept (Poster) |
607 |
6.5 |
The Uncanny Similarity of Recurrence and Depth |
6, 6, 6, 8 |
Accept (Poster) |
608 |
6.5 |
Reliable Adversarial Distillation with Unreliable Teachers |
6, 6, 8, 6 |
Accept (Poster) |
609 |
6.5 |
FedPara: Low-rank Hadamard Product for Communication-Efficient Federated Learning |
6, 6, 8, 6 |
Accept (Poster) |
610 |
6.5 |
Learning Features with Parameter-Free Layers |
8, 6, 6, 6 |
Accept (Poster) |
611 |
6.5 |
How to deal with missing data in supervised deep learning? |
8, 5, 5, 8 |
Accept (Poster) |
612 |
6.5 |
Stiffness-aware neural network for learning Hamiltonian systems |
8, 6, 6, 6 |
Accept (Poster) |
613 |
6.5 |
Model-Based Offline Meta-Reinforcement Learning with Regularization |
6, 6, 6, 8 |
Accept (Poster) |
614 |
6.5 |
Improving the Accuracy of Learning Example Weights for Imbalance Classification |
6, 6, 8, 6 |
Accept (Poster) |
615 |
6.5 |
Gradient Step Denoiser for convergent Plug-and-Play |
6, 8, 6, 6 |
Accept (Poster) |
616 |
6.5 |
Discovering Latent Concepts Learned in BERT |
5, 8, 5, 8 |
Accept (Poster) |
617 |
6.5 |
Dealing with Non-Stationarity in MARL via Trust-Region Decomposition |
8, 6, 6, 6 |
Accept (Poster) |
618 |
6.5 |
On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning |
8, 5, 5, 8 |
Accept (Poster) |
619 |
6.5 |
Fast Generic Interaction Detection for Model Interpretability and Compression |
6, 8, 6, 6 |
Accept (Poster) |
620 |
6.5 |
F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization |
10, 5, 5, 6 |
Accept (Oral) |
621 |
6.5 |
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training |
6, 6, 8, 6 |
Accept (Poster) |
622 |
6.5 |
DEGREE: Decomposition Based Explanation for Graph Neural Networks |
6, 6, 8, 6 |
Accept (Poster) |
623 |
6.5 |
Decision boundary variability and generalization in neural networks |
8, 6, 6, 6 |
Reject |
624 |
6.5 |
PAC Prediction Sets Under Covariate Shift |
8, 6, 6, 6 |
Accept (Poster) |
625 |
6.5 |
Defending Against Image Corruptions Through Adversarial Augmentations |
8, 6, 6, 6 |
Accept (Poster) |
626 |
6.5 |
Feature Kernel Distillation |
6, 6, 8, 6 |
Accept (Poster) |
627 |
6.5 |
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models |
6, 6, 8, 6 |
Accept (Poster) |
628 |
6.5 |
Learning to Downsample for Segmentation of Ultra-High Resolution Images |
8, 6, 6, 6 |
Accept (Poster) |
629 |
6.5 |
IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes |
6, 6, 6, 8 |
Accept (Poster) |
630 |
6.5 |
Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting |
8, 5, 5, 8 |
Accept (Poster) |
631 |
6.5 |
Learning Prototype-oriented Set Representations for Meta-Learning |
6, 8, 6, 6 |
Accept (Poster) |
632 |
6.5 |
The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models |
6, 6, 6, 8 |
Accept (Poster) |
633 |
6.5 |
Trivial or Impossible --- dichotomous data difficulty masks model differences (on ImageNet and beyond) |
6, 8, 6, 6 |
Accept (Poster) |
634 |
6.5 |
How Did the Model Change? Efficiently Assessing Machine Learning API Shifts |
6, 6, 8, 6 |
Accept (Poster) |
635 |
6.5 |
NormFormer: Improved Transformer Pretraining with Extra Normalization |
8, 8, 5, 5 |
Reject |
636 |
6.5 |
Simple GNN Regularisation for 3D Molecular Property Prediction and Beyond |
8, 6, 6, 6 |
Accept (Poster) |
637 |
6.5 |
What Do We Mean by Generalization in Federated Learning? |
6, 6, 8, 6 |
Accept (Poster) |
638 |
6.5 |
Boosting the Confidence of Near-Tight Generalization Bounds for Uniformly Stable Randomized Algorithms |
8, 6, 6, 6 |
Reject |
639 |
6.5 |
Spread Spurious Attribute: Improving Worst-group Accuracy with Spurious Attribute Estimation |
6, 8, 6, 6 |
Accept (Poster) |
640 |
6.5 |
Trigger Hunting with a Topological Prior for Trojan Detection |
8, 5, 8, 5 |
Accept (Poster) |
641 |
6.5 |
Transferring Hierarchical Structure with Dual Meta Imitation Learning |
8, 6, 6, 6 |
Reject |
642 |
6.5 |
On Evaluation Metrics for Graph Generative Models |
8, 6, 6, 6 |
Accept (Poster) |
643 |
6.5 |
Learning Curves for Gaussian Process Regression with Power-Law Priors and Targets |
6, 8, 6, 6 |
Accept (Poster) |
644 |
6.5 |
Lipschitz-constrained Unsupervised Skill Discovery |
6, 8, 6, 6 |
Accept (Poster) |
645 |
6.5 |
Self-Supervised Inference in State-Space Models |
6, 6, 8, 6 |
Accept (Poster) |
646 |
6.5 |
Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning |
6, 6, 8, 6 |
Accept (Poster) |
647 |
6.5 |
Hierarchical Few-Shot Imitation with Skill Transition Models |
6, 8, 6, 6 |
Accept (Poster) |
648 |
6.5 |
Efficient and Differentiable Conformal Prediction with General Function Classes |
6, 6, 6, 8 |
Accept (Poster) |
649 |
6.5 |
Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks |
6, 6, 6, 8 |
Accept (Poster) |
650 |
6.5 |
Declarative nets that are equilibrium models |
6, 6, 6, 8 |
Accept (Poster) |
651 |
6.5 |
Shallow and Deep Networks are Near-Optimal Approximators of Korobov Functions |
6, 8, 6, 6 |
Accept (Poster) |
652 |
6.5 |
$\beta$-Intact-VAE: Identifying and Estimating Causal Effects under Limited Overlap |
8, 6, 6, 6 |
Accept (Poster) |
653 |
6.5 |
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation |
6, 8, 6, 6 |
Accept (Poster) |
654 |
6.5 |
Understanding Intrinsic Robustness Using Label Uncertainty |
6, 8, 6, 6 |
Accept (Poster) |
655 |
6.5 |
WaveCorr: Deep Reinforcement Learning with Permutation Invariant Policy Networks for Portfolio Management |
8, 5, 5, 8 |
Reject |
656 |
6.5 |
Capturing Structural Locality in Non-parametric Language Models |
6, 6, 8, 6 |
Accept (Poster) |
657 |
6.5 |
On the relation between statistical learning and perceptual distances |
6, 6, 6, 8 |
Accept (Spotlight) |
658 |
6.5 |
Preference Conditioned Neural Multi-objective Combinatorial Optimization |
6, 6, 8, 6 |
Accept (Poster) |
659 |
6.5 |
Minimizing Memorization in Meta-learning: A Causal Perspective |
6, 6, 6, 8 |
Unknown |
660 |
6.4 |
WeakM3D: Towards Weakly Supervised Monocular 3D Object Detection |
6, 8, 6, 6, 6 |
Accept (Poster) |
661 |
6.4 |
A Geometric Perspective on Variational Autoencoders |
8, 6, 6, 6, 6 |
Reject |
662 |
6.4 |
Designing Less Forgetful Networks for Continual Learning |
5, 5, 8, 6, 8 |
Reject |
663 |
6.4 |
Learning to Schedule Learning rate with Graph Neural Networks |
6, 6, 6, 8, 6 |
Accept (Poster) |
664 |
6.4 |
It Takes Two to Tango: Mixup for Deep Metric Learning |
8, 6, 6, 6, 6 |
Accept (Poster) |
665 |
6.4 |
Graph Neural Networks with Learnable Structural and Positional Representations |
5, 5, 8, 8, 6 |
Accept (Poster) |
666 |
6.4 |
Iterative Bilinear Temporal-Spectral Fusion for Unsupervised Representation Learning in Time Series |
6, 6, 6, 8, 6 |
Unknown |
667 |
6.4 |
On the Role of Neural Collapse in Transfer Learning |
6, 6, 8, 6, 6 |
Accept (Poster) |
668 |
6.4 |
ViTGAN: Training GANs with Vision Transformers |
6, 8, 6, 6, 6 |
Accept (Spotlight) |
669 |
6.4 |
GRAND++: Graph Neural Diffusion with A Source Term |
6, 6, 6, 6, 8 |
Accept (Poster) |
670 |
6.4 |
Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents |
5, 6, 8, 8, 5 |
Reject |
671 |
6.4 |
Predictive Modeling in the Presence of Nuisance-Induced Spurious Correlations |
5, 8, 5, 8, 6 |
Accept (Poster) |
672 |
6.4 |
Gradient Matching for Domain Generalization |
6, 8, 6, 6, 6 |
Accept (Poster) |
673 |
6.33 |
ViDT: An Efficient and Effective Fully Transformer-based Object Detector |
5, 6, 8 |
Accept (Poster) |
674 |
6.33 |
Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information |
8, 6, 5 |
Accept (Poster) |
675 |
6.33 |
If your data distribution shifts, use self-learning |
6, 5, 8 |
Reject |
676 |
6.33 |
A Neural Tangent Kernel Perspective of Infinite Tree Ensembles |
3, 8, 8 |
Accept (Poster) |
677 |
6.33 |
Pseudo-Labeled Auto-Curriculum Learning for Semi-Supervised Keypoint Localization |
6, 8, 5 |
Accept (Poster) |
678 |
6.33 |
Recurrent Model-Free RL is a Strong Baseline for Many POMDPs |
6, 8, 5 |
Reject |
679 |
6.33 |
Pareto Policy Adaptation |
6, 8, 5 |
Accept (Poster) |
680 |
6.33 |
CrowdPlay: Crowdsourcing human demonstration data for offline learning in Atari games |
8, 5, 6 |
Accept (Poster) |
681 |
6.33 |
Neural Models for Output-Space Invariance in Combinatorial Problems |
5, 6, 8 |
Accept (Poster) |
682 |
6.33 |
Transformers Can Do Bayesian Inference |
8, 5, 6 |
Accept (Poster) |
683 |
6.33 |
Hierarchical Variational Memory for Few-shot Learning Across Domains |
6, 5, 8 |
Accept (Poster) |
684 |
6.33 |
Information-theoretic Online Memory Selection for Continual Learning |
8, 5, 6 |
Accept (Poster) |
685 |
6.33 |
MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining |
8, 5, 6 |
Accept (Poster) |
686 |
6.33 |
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer |
8, 6, 5 |
Accept (Poster) |
687 |
6.33 |
Natural Attribute-based Shift Detection |
6, 5, 8 |
Reject |
688 |
6.33 |
Neural Networks as Kernel Learners: The Silent Alignment Effect |
8, 6, 5 |
Accept (Poster) |
689 |
6.33 |
Bridging Recommendation and Marketing via Recurrent Intensity Modeling |
5, 8, 6 |
Accept (Poster) |
690 |
6.33 |
Learning to Map for Active Semantic Goal Navigation |
5, 8, 6 |
Accept (Poster) |
691 |
6.33 |
Rethinking Goal-Conditioned Supervised Learning and Its Connection to Offline RL |
5, 8, 6 |
Accept (Poster) |
692 |
6.33 |
Learning Distributionally Robust Models at Scale via Composite Optimization |
6, 5, 8 |
Accept (Poster) |
693 |
6.33 |
Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring |
5, 8, 6 |
Accept (Poster) |
694 |
6.33 |
Public Data-Assisted Mirror Descent for Private Model Training |
8, 6, 5 |
Reject |
695 |
6.33 |
Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift |
6, 8, 5 |
Accept (Poster) |
696 |
6.33 |
Sparse Attention with Learning to Hash |
8, 6, 5 |
Accept (Poster) |
697 |
6.33 |
Using Graph Representation Learning with Schema Encoders to Measure the Severity of Depressive Symptoms |
8, 6, 5 |
Accept (Poster) |
698 |
6.33 |
Distilling GANs with Style-Mixed Triplets for X2I Translation with Limited Data |
8, 6, 5 |
Accept (Poster) |
699 |
6.33 |
On the Convergence of Certified Robust Training with Interval Bound Propagation |
5, 8, 6 |
Accept (Poster) |
700 |
6.33 |
Non-Autoregressive Models are Better Multilingual Translators |
6, 5, 8 |
Accept (Poster) |
701 |
6.33 |
Autonomous Learning of Object-Centric Abstractions for High-Level Planning |
5, 6, 8 |
Accept (Poster) |
702 |
6.33 |
Learning Similarity Metrics for Volumetric Simulations with Multiscale CNNs |
3, 8, 8 |
Reject |
703 |
6.33 |
Unified Visual Transformer Compression |
5, 8, 6 |
Accept (Poster) |
704 |
6.33 |
Incremental False Negative Detection for Contrastive Learning |
8, 5, 6 |
Accept (Poster) |
705 |
6.33 |
Robust Cross-Modal Semi-supervised Few Shot Learning |
5, 8, 6 |
Reject |
706 |
6.33 |
Fine-grained Differentiable Physics: A Yarn-level Model for Fabrics |
6, 8, 6, 6, 6, 6 |
Accept (Poster) |
707 |
6.33 |
Generative Principal Component Analysis |
5, 8, 6 |
Accept (Poster) |
708 |
6.33 |
Independent Component Alignment for Multi-task Learning |
8, 5, 6 |
Reject |
709 |
6.33 |
Counterfactual Plans under Distributional Ambiguity |
5, 6, 8 |
Accept (Poster) |
710 |
6.33 |
Language-driven Semantic Segmentation |
6, 8, 5 |
Accept (Poster) |
711 |
6.33 |
Concurrent Adversarial Learning for Large-Batch Training |
8, 5, 6 |
Accept (Poster) |
712 |
6.33 |
Anti-Concentrated Confidence Bonuses For Scalable Exploration |
8, 6, 5 |
Accept (Poster) |
713 |
6.33 |
DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR |
6, 8, 5 |
Accept (Poster) |
714 |
6.33 |
Eliminating Sharp Minima from SGD with Truncated Heavy-tailed Noise |
6, 8, 5 |
Accept (Poster) |
715 |
6.33 |
Neural Solvers for Fast and Accurate Numerical Optimal Control |
6, 8, 5 |
Accept (Poster) |
716 |
6.33 |
Complex-valued deep learning with differential privacy |
5, 6, 8 |
Reject |
717 |
6.33 |
Mapping conditional distributions for domain adaptation under generalized target shift |
8, 6, 5 |
Accept (Poster) |
718 |
6.33 |
Auto-scaling Vision Transformers without Training |
5, 6, 8 |
Accept (Poster) |
719 |
6.33 |
Optimal Representations for Covariate Shift |
6, 5, 8 |
Accept (Poster) |
720 |
6.33 |
Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspective |
6, 8, 5 |
Accept (Poster) |
721 |
6.25 |
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods |
6, 5, 6, 8 |
Accept (Poster) |
722 |
6.25 |
Hindsight Foresight Relabeling for Meta-Reinforcement Learning |
6, 6, 8, 5 |
Accept (Poster) |
723 |
6.25 |
Step-unrolled Denoising Autoencoders for Text Generation |
8, 6, 5, 6 |
Accept (Poster) |
724 |
6.25 |
Recursive Construction of Stable Assemblies of Recurrent Neural Networks |
5, 6, 8, 6 |
Reject |
725 |
6.25 |
Do deep networks transfer invariances across classes? |
8, 6, 5, 6 |
Accept (Poster) |
726 |
6.25 |
Self-ensemble Adversarial Training for Improved Robustness |
8, 5, 6, 6 |
Accept (Poster) |
727 |
6.25 |
Heteroscedastic Temporal Variational Autoencoder For Irregularly Sampled Time Series |
6, 6, 8, 5 |
Accept (Poster) |
728 |
6.25 |
FedBABU: Toward Enhanced Representation for Federated Image Classification |
8, 6, 6, 5 |
Accept (Poster) |
729 |
6.25 |
Curriculum learning as a tool to uncover learning principles in the brain |
5, 8, 6, 6 |
Accept (Poster) |
730 |
6.25 |
Lossless Compression with Probabilistic Circuits |
6, 5, 8, 6 |
Accept (Spotlight) |
731 |
6.25 |
Collapse by Conditioning: Training Class-conditional GANs with Limited Data |
5, 8, 6, 6 |
Accept (Poster) |
732 |
6.25 |
An Autoregressive Flow Model for 3D Molecular Geometry Generation from Scratch |
6, 8, 6, 5 |
Accept (Poster) |
733 |
6.25 |
Blaschke Product Neural Networks (BPNN): A Physics-Infused Neural Network for Phase Retrieval of Meromorphic Functions |
6, 5, 8, 6 |
Accept (Poster) |
734 |
6.25 |
Model Zoo: A Growing Brain That Learns Continually |
5, 8, 6, 6 |
Accept (Poster) |
735 |
6.25 |
Generalized Kernel Thinning |
6, 5, 8, 6 |
Accept (Poster) |
736 |
6.25 |
Learning curves for continual learning in neural networks: Self-knowledge transfer and forgetting |
5, 6, 6, 8 |
Accept (Poster) |
737 |
6.25 |
TAda! Temporally-Adaptive Convolutions for Video Understanding |
6, 8, 6, 5 |
Accept (Poster) |
738 |
6.25 |
How Much Can CLIP Benefit Vision-and-Language Tasks? |
6, 5, 6, 8 |
Accept (Poster) |
739 |
6.25 |
Neural Markov Controlled SDE: Stochastic Optimization for Continuous-Time Data |
8, 3, 6, 8 |
Accept (Poster) |
740 |
6.25 |
It Takes Four to Tango: Multiagent Self Play for Automatic Curriculum Generation |
6, 5, 6, 8 |
Accept (Poster) |
741 |
6.25 |
Transferable Visual Control Policies Through Robot-Awareness |
5, 6, 6, 8 |
Accept (Poster) |
742 |
6.25 |
Fast Model Editing at Scale |
6, 3, 8, 8 |
Accept (Poster) |
743 |
6.25 |
Domain-wise Adversarial Training for Out-of-Distribution Generalization |
8, 6, 5, 6 |
Reject |
744 |
6.25 |
Fairness Guarantees under Demographic Shift |
8, 6, 5, 6 |
Accept (Poster) |
745 |
6.25 |
Graph Auto-Encoder via Neighborhood Wasserstein Reconstruction |
8, 6, 6, 5 |
Accept (Poster) |
746 |
6.25 |
Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings |
8, 8, 6, 3 |
Accept (Poster) |
747 |
6.25 |
Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients |
8, 5, 6, 6 |
Accept (Poster) |
748 |
6.25 |
TRGP: Trust Region Gradient Projection for Continual Learning |
8, 8, 6, 3 |
Accept (Spotlight) |
749 |
6.25 |
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning |
8, 6, 6, 5 |
Accept (Poster) |
750 |
6.25 |
Structure by Architecture: Disentangled Representations without Regularization |
6, 8, 5, 6 |
Reject |
751 |
6.25 |
Large-Scale Representation Learning on Graphs via Bootstrapping |
6, 8, 6, 5 |
Accept (Poster) |
752 |
6.25 |
Max-Affine Spline Insights Into Deep Network Pruning |
6, 6, 5, 8 |
Reject |
753 |
6.25 |
Neural Contextual Bandits with Deep Representation and Shallow Exploration |
6, 8, 3, 8 |
Accept (Poster) |
754 |
6.25 |
GATSBI: Generative Adversarial Training for Simulation-Based Inference |
6, 5, 6, 8 |
Accept (Poster) |
755 |
6.25 |
Universal Joint Approximation of Manifolds and Densities by Simple Injective Flows |
5, 6, 6, 8 |
Reject |
756 |
6.25 |
Is Importance Weighting Incompatible with Interpolating Classifiers? |
6, 5, 6, 8 |
Accept (Poster) |
757 |
6.25 |
Memorizing Transformers |
6, 5, 6, 8 |
Accept (Spotlight) |
758 |
6.25 |
Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL |
6, 8, 3, 8 |
Accept (Poster) |
759 |
6.25 |
Deep Point Cloud Reconstruction |
6, 6, 8, 5 |
Accept (Poster) |
760 |
6.25 |
Online approximate factorization of a kernel matrix by a Hebbian neural network |
8, 5, 6, 6 |
Reject |
761 |
6.25 |
Differentiable Gradient Sampling for Learning Implicit 3D Scene Reconstructions from a Single Image |
5, 8, 6, 6 |
Accept (Poster) |
762 |
6.25 |
Neural Parameter Allocation Search |
5, 6, 8, 6 |
Accept (Poster) |
763 |
6.25 |
Conditional Contrastive Learning with Kernel |
8, 6, 6, 5 |
Accept (Poster) |
764 |
6.25 |
Goal-Directed Planning via Hindsight Experience Replay |
8, 3, 8, 6 |
Accept (Poster) |
765 |
6.25 |
Evidential Turing Processes |
6, 6, 5, 8 |
Accept (Poster) |
766 |
6.25 |
DARA: Dynamics-Aware Reward Augmentation in Offline Reinforcement Learning |
5, 8, 6, 6 |
Accept (Poster) |
767 |
6.25 |
Linking Emergent and Natural Languages via Corpus Transfer |
3, 8, 6, 8 |
Accept (Spotlight) |
768 |
6.25 |
Weight Expansion: A New Perspective on Dropout and Generalization |
6, 5, 8, 6 |
Unknown |
769 |
6.25 |
Automated Self-Supervised Learning for Graphs |
6, 8, 5, 6 |
Accept (Poster) |
770 |
6.25 |
FastSHAP: Real-Time Shapley Value Estimation |
6, 8, 6, 5 |
Accept (Poster) |
771 |
6.25 |
Memory Augmented Optimizers for Deep Learning |
5, 6, 6, 8 |
Accept (Poster) |
772 |
6.25 |
Subjective Learning for Open-Ended Data |
6, 8, 6, 5 |
Reject |
773 |
6.25 |
Faster No-Regret Learning Dynamics for Extensive-Form Correlated Equilibrium |
8, 6, 6, 5 |
Reject |
774 |
6.25 |
Adversarial Retriever-Ranker for Dense Text Retrieval |
5, 8, 6, 6 |
Accept (Poster) |
775 |
6.25 |
Boosting the Certified Robustness of L-infinity Distance Nets |
6, 5, 6, 8 |
Accept (Poster) |
776 |
6.25 |
Neural Processes with Stochastic Attention: Paying more attention to the context dataset |
6, 6, 5, 8 |
Accept (Poster) |
777 |
6.25 |
Provable Learning-based Algorithm For Sparse Recovery |
8, 6, 6, 5 |
Accept (Poster) |
778 |
6.25 |
Top-N: Equivariant Set and Graph Generation without Exchangeability |
6, 6, 8, 5 |
Accept (Poster) |
779 |
6.25 |
Multi-Agent MDP Homomorphic Networks |
6, 6, 8, 5 |
Accept (Poster) |
780 |
6.25 |
Igeood: An Information Geometry Approach to Out-of-Distribution Detection |
6, 6, 8, 5 |
Accept (Poster) |
781 |
6.25 |
On feature learning in shallow and multi-layer neural networks with global convergence guarantees |
6, 8, 8, 3 |
Accept (Poster) |
782 |
6.25 |
Online Coreset Selection for Rehearsal-based Continual Learning |
6, 6, 8, 5 |
Accept (Poster) |
783 |
6.25 |
Switch to Generalize: Domain-Switch Learning for Cross-Domain Few-Shot Classification |
6, 6, 5, 8 |
Accept (Poster) |
784 |
6.25 |
How Low Can We Go: Trading Memory for Error in Low-Precision Training |
8, 6, 6, 5 |
Accept (Poster) |
785 |
6.25 |
CADDA: Class-wise Automatic Differentiable Data Augmentation for EEG Signals |
6, 6, 8, 5 |
Accept (Poster) |
786 |
6.25 |
A Biologically Interpretable Graph Convolutional Network to Link Genetic Risk Pathways and Imaging Phenotypes of Disease |
6, 8, 5, 6 |
Accept (Poster) |
787 |
6.25 |
Connectome-constrained Latent Variable Model of Whole-Brain Neural Activity |
6, 8, 8, 3 |
Accept (Poster) |
788 |
6.25 |
Mirror Descent Policy Optimization |
6, 8, 6, 5 |
Accept (Poster) |
789 |
6.25 |
Relational Multi-Task Learning: Modeling Relations between Data and Tasks |
5, 6, 6, 8 |
Accept (Spotlight) |
790 |
6.25 |
R4D: Utilizing Reference Objects for Long-Range Distance Estimation |
5, 8, 6, 6 |
Accept (Poster) |
791 |
6.25 |
Continual Normalization: Rethinking Batch Normalization for Online Continual Learning |
6, 8, 5, 6 |
Accept (Poster) |
792 |
6.25 |
Finding an Unsupervised Image Segmenter in each of your Deep Generative Models |
8, 6, 5, 6 |
Accept (Poster) |
793 |
6.25 |
Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System |
6, 8, 5, 6 |
Accept (Poster) |
794 |
6.25 |
Evolutionary Diversity Optimization with Clustering-based Selection for Reinforcement Learning |
8, 6, 5, 6 |
Accept (Poster) |
795 |
6.25 |
Knowledge Infused Decoding |
6, 8, 5, 6 |
Accept (Poster) |
796 |
6.25 |
SUMNAS: Supernet with Unbiased Meta-Features for Neural Architecture Search |
6, 6, 5, 8 |
Accept (Poster) |
797 |
6.25 |
Online Continual Learning on Class Incremental Blurry Task Configuration with Anytime Inference |
8, 3, 8, 6 |
Accept (Poster) |
798 |
6.25 |
Distributional Reinforcement Learning with Monotonic Splines |
5, 8, 6, 6 |
Accept (Poster) |
799 |
6.25 |
End-to-End Balancing for Causal Continuous Treatment-Effect Estimation |
3, 8, 6, 8 |
Reject |
800 |
6.25 |
Learning to Extend Molecular Scaffolds with Structural Motifs |
6, 3, 8, 8 |
Accept (Poster) |
801 |
6.25 |
Scale Efficiently: Insights from Pretraining and Finetuning Transformers |
8, 5, 6, 6 |
Accept (Poster) |
802 |
6.25 |
DriPP: Driven Point Processes to Model Stimuli Induced Patterns in M/EEG Signals |
8, 3, 8, 6 |
Accept (Poster) |
803 |
6.25 |
Autoregressive Diffusion Models |
6, 8, 5, 6 |
Accept (Poster) |
804 |
6.25 |
Understanding and Preventing Capacity Loss in Reinforcement Learning |
8, 8, 6, 3 |
Accept (Spotlight) |
805 |
6.25 |
Target-Side Data Augmentation for Sequence Generation |
8, 6, 6, 5 |
Accept (Poster) |
806 |
6.25 |
Taming Sparsely Activated Transformer with Stochastic Experts |
6, 5, 8, 6 |
Accept (Poster) |
807 |
6.25 |
Variational Inference for Discriminative Learning with Generative Modeling of Feature Incompletion |
5, 8, 6, 6 |
Accept (Oral) |
808 |
6.25 |
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation |
8, 6, 5, 6 |
Accept (Poster) |
809 |
6.25 |
ANCER: Anisotropic Certification via Sample-wise Volume Maximization |
6, 6, 5, 8 |
Reject |
810 |
6.25 |
Auditing AI models for Verified Deployment under Semantic Specifications |
8, 6, 5, 6 |
Reject |
811 |
6.25 |
How Well Does Self-Supervised Pre-Training Perform with Streaming Data? |
6, 8, 5, 6 |
Accept (Poster) |
812 |
6.25 |
A global convergence theory for deep ReLU implicit networks via over-parameterization |
3, 6, 8, 8 |
Accept (Poster) |
813 |
6.25 |
Semi-relaxed Gromov-Wasserstein divergence and applications on graphs |
6, 6, 5, 8 |
Accept (Poster) |
814 |
6.25 |
Generalization in Deep RL for TSP Problems via Equivariance and Local Search |
5, 8, 6, 6 |
Reject |
815 |
6.25 |
Robust Losses for Learning Value Functions |
6, 6, 8, 5 |
Reject |
816 |
6.25 |
CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery |
3, 8, 8, 6 |
Reject |
817 |
6.25 |
Learning Pruning-Friendly Networks via Frank-Wolfe: One-Shot, Any-Sparsity, And No Retraining |
5, 8, 6, 6 |
Accept (Spotlight) |
818 |
6.25 |
Unsupervised Disentanglement with Tensor Product Representations on the Torus |
8, 6, 8, 3 |
Accept (Poster) |
819 |
6.25 |
Implicit Bias of MSE Gradient Optimization in Underparameterized Neural Networks |
6, 8, 5, 6 |
Accept (Poster) |
820 |
6.25 |
NViT: Vision Transformer Compression and Parameter Redistribution |
6, 6, 8, 5 |
Unknown |
821 |
6.25 |
Maximum Entropy RL (Provably) Solves Some Robust RL Problems |
5, 6, 8, 6 |
Accept (Poster) |
822 |
6.25 |
FrugalMCT: Efficient Online ML API Selection for Multi-Label Classification Tasks |
6, 8, 8, 3 |
Reject |
823 |
6.25 |
Gaussian Mixture Convolution Networks |
5, 6, 8, 6 |
Accept (Poster) |
824 |
6.25 |
Neural Link Prediction with Walk Pooling |
5, 6, 6, 8 |
Accept (Poster) |
825 |
6.25 |
Quadtree Attention for Vision Transformers |
6, 5, 8, 6 |
Accept (Poster) |
826 |
6.25 |
Encoding Weights of Irregular Sparsity for Fixed-to-Fixed Model Compression |
8, 5, 6, 6 |
Accept (Poster) |
827 |
6.25 |
Normalized Attention Without Probability Cage |
6, 5, 6, 8 |
Reject |
828 |
6.25 |
Meta-Learning Dynamics Forecasting Using Task Inference |
6, 5, 8, 6 |
Reject |
829 |
6.25 |
Learning Value Functions from Undirected State-only Experience |
6, 6, 8, 5 |
Accept (Poster) |
830 |
6.25 |
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention |
6, 6, 5, 8 |
Accept (Poster) |
831 |
6.25 |
Resonance in Weight Space: Covariate Shift Can Drive Divergence of SGD with Momentum |
3, 8, 6, 8 |
Accept (Poster) |
832 |
6.25 |
Enabling Arbitrary Translation Objectives with Adaptive Tree Search |
8, 5, 6, 6 |
Accept (Poster) |
833 |
6.25 |
GDA-AM: ON THE EFFECTIVENESS OF SOLVING MIN-IMAX OPTIMIZATION VIA ANDERSON MIXING |
5, 8, 6, 6 |
Accept (Poster) |
834 |
6.25 |
Multitask Prompted Training Enables Zero-Shot Task Generalization |
8, 6, 3, 8 |
Accept (Spotlight) |
835 |
6.25 |
Constraining Linear-chain CRFs to Regular Languages |
6, 6, 8, 5 |
Accept (Poster) |
836 |
6.25 |
Rethinking Class-Prior Estimation for Positive-Unlabeled Learning |
5, 8, 6, 6 |
Accept (Poster) |
837 |
6.25 |
Increasing the Cost of Model Extraction with Calibrated Proof of Work |
8, 8, 3, 6 |
Accept (Spotlight) |
838 |
6.25 |
The Evolution of Uncertainty of Learning in Games |
5, 8, 6, 6 |
Accept (Poster) |
839 |
6.25 |
Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage |
5, 8, 6, 6 |
Accept (Poster) |
840 |
6.25 |
CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting |
8, 6, 6, 5 |
Accept (Poster) |
841 |
6.25 |
Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation |
6, 6, 8, 5 |
Reject |
842 |
6.25 |
The Essential Elements of Offline RL via Supervised Learning |
6, 5, 6, 8 |
Accept (Poster) |
843 |
6.25 |
Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism |
5, 6, 6, 8 |
Accept (Poster) |
844 |
6.25 |
Generative Modeling with Optimal Transport Maps |
5, 6, 8, 6 |
Accept (Poster) |
845 |
6.25 |
Scale Mixtures of Neural Network Gaussian Processes |
8, 6, 6, 5 |
Accept (Poster) |
846 |
6.25 |
On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport |
6, 8, 6, 5 |
Reject |
847 |
6.25 |
Multi-Task Processes |
6, 8, 5, 6 |
Accept (Poster) |
848 |
6.25 |
Discriminative Similarity for Data Clustering |
5, 8, 6, 6 |
Accept (Poster) |
849 |
6.25 |
Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models |
5, 6, 8, 6 |
Accept (Poster) |
850 |
6.25 |
Expressivity of Emergent Languages is a Trade-off between Contextual Complexity and Unpredictability |
6, 8, 3, 8 |
Accept (Poster) |
851 |
6.25 |
Monotonic Differentiable Sorting Networks |
5, 6, 6, 8 |
Accept (Poster) |
852 |
6.25 |
AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation |
8, 6, 6, 5 |
Accept (Poster) |
853 |
6.25 |
Multi-Mode Deep Matrix and Tensor Factorization |
6, 5, 6, 8 |
Accept (Poster) |
854 |
6.25 |
Group-based Interleaved Pipeline Parallelism for Large-scale DNN Training |
3, 6, 8, 8 |
Accept (Poster) |
855 |
6.25 |
Privacy-preserving Task-Agnostic Vision Transformer for Image Processing |
5, 6, 6, 8 |
Reject |
856 |
6.25 |
Best Practices in Pool-based Active Learning for Image Classification |
5, 6, 8, 6 |
Reject |
857 |
6.25 |
Explainable GNN-Based Models over Knowledge Graphs |
6, 6, 5, 8 |
Accept (Poster) |
858 |
6.25 |
Synthesising Audio Adversarial Examples for Automatic Speech Recognition |
6, 5, 6, 8 |
Reject |
859 |
6.25 |
Learning Multimodal VAEs through Mutual Supervision |
6, 5, 8, 6 |
Accept (Spotlight) |
860 |
6.25 |
On-Policy Model Errors in Reinforcement Learning |
8, 6, 5, 6 |
Accept (Poster) |
861 |
6.25 |
In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specifications |
8, 8, 3, 6 |
Accept (Poster) |
862 |
6.25 |
Subspace Regularizers for Few-Shot Class Incremental Learning |
5, 8, 6, 6 |
Accept (Poster) |
863 |
6.25 |
RieszNet and ForestRiesz: Automatic Debiased Machine Learning with Neural Nets and Random Forests |
8, 6, 6, 5 |
Reject |
864 |
6.2 |
OBJECT DYNAMICS DISTILLATION FOR SCENE DECOMPOSITION AND REPRESENTATION |
6, 6, 8, 5, 6 |
Accept (Poster) |
865 |
6.2 |
Cross-Domain Lossy Compression as Optimal Transport with an Entropy Bottleneck |
8, 6, 6, 8, 3 |
Accept (Poster) |
866 |
6.2 |
Efficient Neural Causal Discovery without Acyclicity Constraints |
6, 8, 5, 6, 6 |
Accept (Poster) |
867 |
6.2 |
Policy Smoothing for Provably Robust Reinforcement Learning |
5, 6, 6, 8, 6 |
Accept (Poster) |
868 |
6.2 |
A theoretically grounded characterization of feature representations |
6, 5, 8, 6, 6 |
Reject |
869 |
6.2 |
The Spectral Bias of Polynomial Neural Networks |
6, 8, 6, 6, 5 |
Accept (Poster) |
870 |
6.2 |
On Redundancy and Diversity in Cell-based Neural Architecture Search |
6, 6, 8, 6, 5 |
Accept (Poster) |
871 |
6.2 |
NASViT: Neural Architecture Search for Efficient Vision Transformers with Gradient Conflict aware Supernet Training |
6, 8, 6, 5, 6 |
Accept (Poster) |
872 |
6.2 |
Understanding Dimensional Collapse in Contrastive Self-supervised Learning |
5, 6, 8, 6, 6 |
Accept (Poster) |
873 |
6.2 |
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective |
8, 6, 6, 5, 6 |
Accept (Poster) |
874 |
6.2 |
Lower Bounds on the Robustness of Fixed Feature Extractors to Test-time Adversaries |
5, 6, 6, 8, 6 |
Reject |
875 |
6.2 |
BiBERT: Accurate Fully Binarized BERT |
8, 6, 5, 6, 6 |
Accept (Poster) |
876 |
6.2 |
Fair Normalizing Flows |
6, 6, 8, 5, 6 |
Accept (Poster) |
877 |
6.2 |
A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features |
6, 6, 6, 8, 5 |
Accept (Poster) |
878 |
6.2 |
Non-Parallel Text Style Transfer with Self-Parallel Supervision |
6, 3, 8, 6, 8 |
Accept (Poster) |
879 |
6 |
Fact-driven Logical Reasoning |
6, 6, 6, 6 |
Reject |
880 |
6 |
Adversarial Style Transfer for Robust Policy Optimization in Reinforcement Learning |
5, 6, 8, 5 |
Reject |
881 |
6 |
Linear algebra with transformers |
8, 5, 6, 5 |
Reject |
882 |
6 |
ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learning |
6, 6, 6, 6 |
Reject |
883 |
6 |
Fishr: Invariant Gradient Variances for Out-of-distribution Generalization |
5, 8, 3, 8 |
Unknown |
884 |
6 |
Learning Invariant Representations on Multilingual Language Models for Unsupervised Cross-Lingual Transfer |
6, 6, 6, 6 |
Accept (Poster) |
885 |
6 |
Patches Are All You Need? |
5, 5, 8 |
Reject |
886 |
6 |
Normalization of Language Embeddings for Cross-Lingual Alignment |
8, 3, 5, 6, 8 |
Accept (Poster) |
887 |
6 |
Variational Component Decoder for Source Extraction from Nonlinear Mixture |
8, 8, 5, 3 |
Reject |
888 |
6 |
Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups |
8, 5, 6, 5 |
Reject |
889 |
6 |
Exploiting Minimum-Variance Policy Evaluation for Policy Optimization |
6, 3, 10, 5 |
Reject |
890 |
6 |
L0-Sparse Canonical Correlation Analysis |
6, 6, 6, 6 |
Accept (Poster) |
891 |
6 |
Deep Classifiers with Label Noise Modeling and Distance Awareness |
5, 8, 5, 6 |
Reject |
892 |
6 |
GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing |
5, 8, 3, 8 |
Reject |
893 |
6 |
Attentional meta-learners for few-shot polythetic classification |
6, 6, 6, 6 |
Reject |
894 |
6 |
ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind |
6, 6, 6 |
Accept (Poster) |
895 |
6 |
Partial Wasserstein Adversarial Network for Non-rigid Point Set Registration |
6, 6, 6, 6, 6 |
Accept (Poster) |
896 |
6 |
Neural Stochastic Dual Dynamic Programming |
6, 6, 6, 6 |
Accept (Poster) |
897 |
6 |
Repairing Systematic Outliers by Learning Clean Subspaces in VAEs |
6, 6, 6 |
Reject |
898 |
6 |
Zeroth-Order Actor-Critic |
6, 6, 6 |
Reject |
899 |
6 |
Learning Pessimism for Robust and Efficient Off-Policy Reinforcement Learning |
6, 8, 5, 5 |
Unknown |
900 |
6 |
Learning Scenario Representation for Solving Two-stage Stochastic Integer Programs |
6, 6, 6 |
Accept (Poster) |
901 |
6 |
iFlood: A Stable and Effective Regularizer |
6, 6, 6, 6 |
Accept (Poster) |
902 |
6 |
Is Heterophily A Real Nightmare For Graph Neural Networks on Performing Node Classification? |
3, 5, 8, 8 |
Reject |
903 |
6 |
Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs |
5, 8, 6, 5 |
Reject |
904 |
6 |
Relative Molecule Self-Attention Transformer |
6, 6, 6 |
Reject |
905 |
6 |
Differentiable DAG Sampling |
5, 8, 5 |
Accept (Poster) |
906 |
6 |
Counterfactual Graph Learning for Link Prediction |
5, 6, 8, 5 |
Reject |
907 |
6 |
SoftHebb: Bayesian inference in unsupervised Hebbian soft winner-take-all networks |
6, 6, 6, 6 |
Reject |
908 |
6 |
Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles |
6, 5, 8, 5 |
Reject |
909 |
6 |
Adaptive Label Smoothing with Self-Knowledge |
6, 6, 6, 6 |
Reject |
910 |
6 |
Offline Reinforcement Learning with In-sample Q-Learning |
5, 6, 5, 8 |
Accept (Poster) |
911 |
6 |
MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts |
6, 6, 6 |
Accept (Poster) |
912 |
6 |
Variational autoencoders in the presence of low-dimensional data: landscape and implicit bias |
5, 5, 6, 8 |
Accept (Poster) |
913 |
6 |
An Operator Theoretic View On Pruning Deep Neural Networks |
6, 6, 6, 6 |
Accept (Poster) |
914 |
6 |
Online Adversarial Attacks |
8, 6, 5, 5 |
Accept (Poster) |
915 |
6 |
BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models |
5, 8, 3, 8 |
Accept (Poster) |
916 |
6 |
Optimal Transport for Long-Tailed Recognition with Learnable Cost Matrix |
6, 6, 6 |
Accept (Poster) |
917 |
6 |
Fast Adaptive Anomaly Detection |
5, 8, 3, 6, 8 |
Reject |
918 |
6 |
Provably convergent quasistatic dynamics for mean-field two-player zero-sum games |
6, 6, 6, 6 |
Accept (Poster) |
919 |
6 |
Learning Curves for SGD on Structured Features |
8, 6, 5, 5 |
Accept (Poster) |
920 |
6 |
Sample Efficient Stochastic Policy Extragradient Algorithm for Zero-Sum Markov Game |
6, 6, 6, 6, 6 |
Accept (Poster) |
921 |
6 |
Physics Informed Convex Artificial Neural Networks (PICANNs) for Optimal Transport based Density Estimation |
5, 6, 8, 5 |
Reject |
922 |
6 |
On the Convergence of mSGD and AdaGrad for Stochastic Optimization |
6, 6, 6 |
Accept (Poster) |
923 |
6 |
Recursive Disentanglement Network |
6, 6, 6, 6 |
Accept (Poster) |
924 |
6 |
TPU-GAN: Learning temporal coherence from dynamic point cloud sequences |
6, 6, 6, 6, 6 |
Accept (Poster) |
925 |
6 |
Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval |
6, 6, 6, 6 |
Accept (Poster) |
926 |
6 |
On Robust Prefix-Tuning for Text Classification |
6, 6, 6, 6 |
Accept (Poster) |
927 |
6 |
Programmable 3D snapshot microscopy with Fourier convolutional networks |
6, 6, 6, 6 |
Reject |
928 |
6 |
ZenDet: Revisiting Efficient Object Detection Backbones from Zero-Shot Neural Architecture Search |
6, 6, 6 |
Reject |
929 |
6 |
Zero-Cost Operation Scoring in Differentiable Architecture Search |
8, 6, 5, 5 |
Reject |
930 |
6 |
Communication-Efficient Actor-Critic Methods for Homogeneous Markov Games |
6, 6, 6, 6 |
Accept (Poster) |
931 |
6 |
High Fidelity Visualization of What Your Self-Supervised Representation Knows About |
5, 6, 5, 8 |
Reject |
932 |
6 |
Sample and Communication-Efficient Decentralized Actor-Critic Algorithms with Finite-Time Analysis |
6, 5, 5, 8 |
Reject |
933 |
6 |
Effects of Data Geometry in Early Deep Learning |
8, 5, 6, 5 |
Reject |
934 |
6 |
Training Transition Policies via Distribution Matching for Complex Tasks |
6, 6, 6 |
Accept (Poster) |
935 |
6 |
How Attentive are Graph Attention Networks? |
5, 5, 6, 8 |
Accept (Poster) |
936 |
6 |
How to measure deep uncertainty estimation performance and which models are naturally better at providing it |
5, 5, 6, 8, 6 |
Reject |
937 |
6 |
Self-Supervised Structured Representations for Deep Reinforcement Learning |
5, 6, 5, 8 |
Reject |
938 |
6 |
Treatment effect estimation with confounder balanced instrumental variable regression |
6, 6, 6, 6 |
Unknown |
939 |
6 |
Neural Simulated Annealing |
6, 5, 5, 8 |
Reject |
940 |
6 |
Information-Aware Time Series Meta-Contrastive Learning |
5, 10, 3, 6 |
Reject |
941 |
6 |
Thinking Deeper With Recurrent Networks: Logical Extrapolation Without Overthinking |
8, 6, 5, 5 |
Reject |
942 |
6 |
PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series |
6, 6, 6, 6 |
Accept (Poster) |
943 |
6 |
The Efficiency Misnomer |
8, 5, 6, 5 |
Accept (Poster) |
944 |
6 |
Towards Training Billion Parameter Graph Neural Networks for Atomic Simulations |
8, 5, 6, 5 |
Accept (Poster) |
945 |
6 |
The Rich Get Richer: Disparate Impact of Semi-Supervised Learning |
6, 6, 6, 6 |
Accept (Poster) |
946 |
6 |
CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP |
8, 5, 6, 5 |
Reject |
947 |
6 |
Dropout Q-Functions for Doubly Efficient Reinforcement Learning |
6, 6, 6 |
Accept (Poster) |
948 |
6 |
On the role of population heterogeneity in emergent communication |
6, 6, 6, 6 |
Accept (Poster) |
949 |
6 |
Measuring CLEVRness: Black-box Testing of Visual Reasoning Models |
6, 6, 6 |
Accept (Poster) |
950 |
6 |
ST-DDPM: Explore Class Clustering for Conditional Diffusion Probabilistic Models |
6, 6, 6, 6 |
Reject |
951 |
6 |
Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance |
5, 5, 8 |
Reject |
952 |
6 |
OntoProtein: Protein Pretraining With Gene Ontology Embedding |
6, 6, 6 |
Accept (Poster) |
953 |
6 |
Orchestrated Value Mapping for Reinforcement Learning |
6, 6, 6 |
Accept (Poster) |
954 |
6 |
Offline Neural Contextual Bandits: Pessimism, Optimization and Generalization |
6, 6, 6, 6 |
Accept (Poster) |
955 |
6 |
Evaluating Disentanglement of Structured Latent Representations |
6, 6, 6 |
Accept (Poster) |
956 |
6 |
Conditional GANs with Auxiliary Discriminative Classifier |
5, 6, 5, 8 |
Reject |
957 |
6 |
Mistill: Distilling Distributed Network Protocols from Examples |
8, 5, 5, 6 |
Reject |
958 |
6 |
Do Users Benefit From Interpretable Vision? A User Study, Baseline, And Dataset |
6, 5, 5, 8 |
Accept (Poster) |
959 |
6 |
GrASP: Gradient-Based Affordance Selection for Planning |
6, 5, 5, 8 |
Reject |
960 |
6 |
Controlling the Complexity and Lipschitz Constant improves Polynomial Nets |
5, 6, 8, 5 |
Accept (Poster) |
961 |
6 |
Distribution Matching in Deep Generative Models with Kernel Transfer Operators |
6, 6, 6, 6 |
Reject |
962 |
6 |
Indiscriminate Poisoning Attacks Are Shortcuts |
5, 3, 8, 8 |
Reject |
963 |
6 |
Topological Graph Neural Networks |
6, 6, 6, 6 |
Accept (Poster) |
964 |
6 |
How BPE Affects Memorization in Transformers |
6, 6, 6 |
Reject |
965 |
6 |
MoReL: Multi-omics Relational Learning |
5, 5, 6, 8 |
Accept (Poster) |
966 |
6 |
Vector-quantized Image Modeling with Improved VQGAN |
6, 6, 6, 6 |
Accept (Poster) |
967 |
6 |
Token Pooling in Vision Transformers |
5, 8, 5 |
Reject |
968 |
6 |
Toward Efficient Low-Precision Training: Data Format Optimization and Hysteresis Quantization |
8, 5, 6, 5 |
Accept (Poster) |
969 |
6 |
Generative Pseudo-Inverse Memory |
5, 8, 5 |
Accept (Poster) |
970 |
6 |
Group equivariant neural posterior estimation |
6, 5, 8, 5 |
Accept (Poster) |
971 |
6 |
A Joint Subspace View to Convolutional Neural Networks |
6, 6, 6, 6, 6 |
Reject |
972 |
6 |
RegionViT: Regional-to-Local Attention for Vision Transformers |
6, 6, 6, 6 |
Accept (Poster) |
973 |
6 |
Lightweight Convolutional Neural Networks By Hypercomplex Parameterization |
5, 5, 6, 8 |
Reject |
974 |
6 |
Safe Linear-Quadratic Dual Control with Almost Sure Performance Guarantee |
5, 5, 8, 6 |
Reject |
975 |
6 |
Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation |
5, 5, 6, 8 |
Reject |
976 |
6 |
Transfer RL across Observation Feature Spaces via Model-Based Regularization |
6, 8, 5, 5 |
Accept (Poster) |
977 |
6 |
Semi-supervised learning of partial differential operators and dynamical flows |
5, 5, 8 |
Reject |
978 |
6 |
Signing the Supermask: Keep, Hide, Invert |
6, 8, 5, 5 |
Accept (Poster) |
979 |
6 |
A Statistical Framework for Efficient Out of Distribution Detection in Deep Neural Networks |
8, 3, 5, 8 |
Accept (Poster) |
980 |
6 |
On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networks |
6, 6, 6 |
Accept (Poster) |
981 |
6 |
IGLU: Efficient GCN Training via Lazy Updates |
6, 6, 6 |
Accept (Poster) |
982 |
6 |
Beyond Target Networks: Improving Deep $Q$-learning with Functional Regularization |
6, 8, 5, 5 |
Reject |
983 |
6 |
EVaDE : Event-Based Variational Thompson Sampling for Model-Based Reinforcement Learning |
8, 5, 5, 6 |
Reject |
984 |
6 |
Space-Time Graph Neural Networks |
8, 5, 5 |
Accept (Poster) |
985 |
6 |
Cluster-based Feature Importance Learning for Electronic Health Record Time-series |
8, 6, 5, 5 |
Reject |
986 |
6 |
Attention-based Interpretability with Concept Transformers |
8, 5, 6, 5 |
Accept (Poster) |
987 |
6 |
Few-Shot Backdoor Attacks on Visual Object Tracking |
6, 6, 6 |
Accept (Poster) |
988 |
6 |
Specialized Transformers: Faster, Smaller and more Accurate NLP Models |
8, 3, 5, 8 |
Reject |
989 |
6 |
Universalizing Weak Supervision |
5, 8, 3, 8 |
Accept (Poster) |
990 |
6 |
Charformer: Fast Character Transformers via Gradient-based Subword Tokenization |
5, 5, 6, 8, 6 |
Accept (Poster) |
991 |
6 |
Hidden Parameter Recurrent State Space Models For Changing Dynamics Scenarios |
5, 8, 5, 6 |
Accept (Poster) |
992 |
6 |
Momentum Doesn't Change The Implicit Bias |
5, 5, 6, 8 |
Reject |
993 |
6 |
ZARTS: On Zero-order Optimization for Neural Architecture Search |
6, 6, 6 |
Reject |
994 |
6 |
Neural Methods for Logical Reasoning over Knowledge Graphs |
5, 6, 5, 8 |
Accept (Poster) |
995 |
6 |
PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior |
6, 6, 6, 6 |
Accept (Poster) |
996 |
6 |
Towards the Memorization Effect of Neural Networks in Adversarial Training |
6, 8, 5, 5 |
Reject |
997 |
6 |
Better state exploration using action sequence equivalence |
5, 5, 8 |
Reject |
998 |
6 |
One After Another: Learning Incremental Skills for a Changing World |
6, 6, 6, 6 |
Accept (Poster) |
999 |
6 |
Givens Coordinate Descent Methods for Rotation Matrix Learning in Trainable Embedding Indexes |
6, 6, 6, 6 |
Accept (Poster) |
1000 |
6 |
Conditioning Sequence-to-sequence Networks with Learned Activations |
6, 6, 6 |
Accept (Poster) |
1001 |
6 |
Transfer Learning for Bayesian HPO with End-to-End Meta-Features |
5, 6, 8, 6, 5 |
Reject |
1002 |
6 |
Graph-Enhanced Exploration for Goal-oriented Reinforcement Learning |
6, 6, 6, 6 |
Accept (Poster) |
1003 |
6 |
$G^3$: Representation Learning and Generation for Geometric Graphs |
8, 3, 5, 8 |
Reject |
1004 |
6 |
GeneDisco: A Benchmark for Experimental Design in Drug Discovery |
6, 6, 6 |
Accept (Poster) |
1005 |
6 |
Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs |
6, 8, 5, 5 |
Reject |
1006 |
6 |
A Theory of Tournament Representations |
8, 6, 5, 5 |
Accept (Poster) |
1007 |
6 |
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training |
6, 5, 8, 5 |
Reject |
1008 |
6 |
MAML is a Noisy Contrastive Learner |
5, 5, 8 |
Accept (Poster) |
1009 |
6 |
The Geometry of Adversarial Subspaces |
6, 6, 6, 6 |
Reject |
1010 |
6 |
New Perspective on the Global Convergence of Finite-Sum Optimization |
6, 6, 6, 6 |
Reject |
1011 |
6 |
Discrete Representations Strengthen Vision Transformer Robustness |
8, 3, 8, 5 |
Accept (Poster) |
1012 |
6 |
Autonomous Reinforcement Learning: Formalism and Benchmarking |
8, 5, 8, 3 |
Accept (Poster) |
1013 |
6 |
VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects |
6, 6, 6 |
Accept (Poster) |
1014 |
6 |
Wisdom of Committees: An Overlooked Approach To Faster and More Accurate Models |
6, 6, 6 |
Accept (Poster) |
1015 |
6 |
CrossMatch: Cross-Classifier Consistency Regularization for Open-Set Single Domain Generalization |
6, 8, 5, 5 |
Accept (Poster) |
1016 |
6 |
Tesseract: Gradient Flip Score to Secure Federated Learning against Model Poisoning Attacks |
5, 6, 5, 8 |
Reject |
1017 |
6 |
Transferable Adversarial Attack based on Integrated Gradients |
5, 8, 6, 5 |
Accept (Poster) |
1018 |
6 |
Adam is no better than normalized SGD: Dissecting how adaptivity improves GAN performance |
5, 5, 8 |
Reject |
1019 |
6 |
Gotta Go Fast When Generating Data with Score-Based Models |
8, 6, 5, 5 |
Reject |
1020 |
6 |
On the Relationship between Heterophily and Robustness of Graph Neural Networks |
5, 6, 8, 5 |
Reject |
1021 |
6 |
THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling |
6, 6, 6, 6 |
Accept (Poster) |
1022 |
6 |
C-MinHash: Improving Minwise Hashing with Circulant Permutation |
6, 5, 5, 8 |
Reject |
1023 |
6 |
LEARNING GUARANTEES FOR GRAPH CONVOLUTIONAL NETWORKS ON THE STOCHASTIC BLOCK MODEL |
5, 8, 5, 6 |
Accept (Poster) |
1024 |
6 |
An Agnostic Approach to Federated Learning with Class Imbalance |
6, 6, 6, 6 |
Accept (Poster) |
1025 |
6 |
Generalized Natural Gradient Flows in Hidden Convex-Concave Games and GANs |
6, 6, 6, 6 |
Accept (Poster) |
1026 |
6 |
Sharper Utility Bounds for Differentially Private Models |
5, 5, 8, 6 |
Reject |
1027 |
6 |
Adaptive Cross-Layer Attention for Image Restoration |
6, 8, 5, 5 |
Reject |
1028 |
6 |
Offline Reinforcement Learning for Large Scale Language Action Spaces |
6, 6, 6, 6 |
Accept (Poster) |
1029 |
6 |
Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks |
5, 8, 8, 3 |
Accept (Poster) |
1030 |
6 |
Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation |
5, 6, 5, 8 |
Reject |
1031 |
6 |
Axiomatic Explanations for Visual Search, Retrieval, and Similarity Learning |
6, 6, 6 |
Accept (Poster) |
1032 |
6 |
Self-GenomeNet: Self-supervised Learning with Reverse-Complement Context Prediction for Nucleotide-level Genomics Data |
6, 8, 5, 5 |
Reject |
1033 |
6 |
Decoupled Kernel Neural Processes: Neural Network-Parameterized Stochastic Processes using Explicit Data-driven Kernel |
5, 6, 5, 8 |
Reject |
1034 |
6 |
Auto-Transfer: Learning to Route Transferable Representations |
6, 6, 6, 6 |
Accept (Poster) |
1035 |
6 |
Directional Domain Generalization |
8, 3, 8, 5 |
Unknown |
1036 |
6 |
Modeling Label Space Interactions in Multi-label Classification using Box Embeddings |
5, 8, 5, 6 |
Accept (Poster) |
1037 |
6 |
Optimizer Amalgamation |
6, 6, 6, 6 |
Accept (Poster) |
1038 |
6 |
Zero-Shot Coordination via Semantic Relationships Between Actions and Observations |
6, 6, 6, 6 |
Reject |
1039 |
6 |
Data Quality Matters For Adversarial Training: An Empirical Study |
6, 6, 6, 6 |
Reject |
1040 |
6 |
Learning Weakly-supervised Contrastive Representations |
8, 6, 5, 5 |
Accept (Poster) |
1041 |
6 |
Multi-agent Performative Prediction: From Global Stability and Optimality to Chaos |
6, 6, 6 |
Reject |
1042 |
6 |
Conditional Expectation based Value Decomposition for Scalable On-Demand Ride Pooling |
5, 8, 5 |
Reject |
1043 |
6 |
Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods |
6, 6, 6, 6 |
Accept (Poster) |
1044 |
6 |
Distance-Based Background Class Regularization for Open-Set Recognition |
8, 5, 5, 6 |
Reject |
1045 |
6 |
Graph-Guided Network for Irregularly Sampled Multivariate Time Series |
8, 5, 5 |
Accept (Poster) |
1046 |
6 |
Image2Point: 3D Point-Cloud Understanding with 2D Image Pretrained Models |
6, 6, 6, 6, 6 |
Reject |
1047 |
6 |
Learning to Dequantise with Truncated Flows |
6, 6, 6 |
Accept (Poster) |
1048 |
6 |
Weakly Supervised Label Learning Flows |
8, 6, 5, 5, 6 |
Reject |
1049 |
6 |
Understanding Metric Learning on Unit Hypersphere and Generating Better Examples for Adversarial Training |
5, 6, 5, 8 |
Reject |
1050 |
6 |
Generalizing Few-Shot NAS with Gradient Matching |
6, 6, 6, 6 |
Accept (Poster) |
1051 |
6 |
HydraSum - Disentangling Stylistic Features in Text Summarization using Multi-Decoder Models |
6, 6, 6, 6 |
Reject |
1052 |
6 |
LIGS: Learnable Intrinsic-Reward Generation Selection for Multi-Agent Learning |
5, 6, 8, 5 |
Accept (Poster) |
1053 |
6 |
SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning |
6, 6, 6 |
Accept (Poster) |
1054 |
6 |
PipeGCN: Efficient Full-Graph Training of Graph Convolutional Networks with Pipelined Feature Communication |
6, 6, 6, 6 |
Accept (Poster) |
1055 |
6 |
Generalization Through the Lens of Leave-One-Out Error |
6, 6, 6 |
Accept (Poster) |
1056 |
6 |
Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning |
6, 6, 6, 6 |
Accept (Poster) |
1057 |
6 |
Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks |
5, 8, 5 |
Unknown |
1058 |
6 |
An Explanation of In-context Learning as Implicit Bayesian Inference |
6, 6, 6, 6 |
Accept (Poster) |
1059 |
6 |
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers |
6, 6, 6, 6 |
Accept (Poster) |
1060 |
6 |
Is Homophily a Necessity for Graph Neural Networks? |
6, 6, 6, 6 |
Accept (Poster) |
1061 |
6 |
Query Embedding on Hyper-Relational Knowledge Graphs |
6, 6, 5, 5, 8 |
Accept (Poster) |
1062 |
6 |
Adaptive Wavelet Transformer Network for 3D Shape Representation Learning |
6, 6, 6, 6 |
Accept (Poster) |
1063 |
6 |
Neural graphical modelling in continuous-time: consistency guarantees and algorithms |
5, 5, 8 |
Accept (Poster) |
1064 |
6 |
Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation |
5, 8, 3, 8 |
Reject |
1065 |
6 |
Wish you were here: Hindsight Goal Selection for long-horizon dexterous manipulation |
6, 6, 6, 6 |
Accept (Poster) |
1066 |
6 |
Learning Graphon Mean Field Games and Approximate Nash Equilibria |
5, 6, 5, 8 |
Accept (Poster) |
1067 |
6 |
Benchmarking the Spectrum of Agent Capabilities |
8, 5, 5, 6 |
Accept (Poster) |
1068 |
6 |
Test Time Robustification of Deep Models via Adaptation and Augmentation |
6, 5, 8, 5 |
Reject |
1069 |
6 |
The Effects of Invertibility on the Representational Complexity of Encoders in Variational Autoencoders |
6, 6, 6 |
Accept (Poster) |
1070 |
6 |
Global Convergence and Stability of Stochastic Gradient Descent |
6, 6, 6 |
Reject |
1071 |
6 |
Language model compression with weighted low-rank factorization |
6, 6, 6 |
Accept (Poster) |
1072 |
6 |
Selective Ensembles for Consistent Predictions |
6, 5, 5, 8 |
Accept (Poster) |
1073 |
6 |
Open-World Semi-Supervised Learning |
6, 6, 6, 6, 6 |
Accept (Poster) |
1074 |
6 |
On the benefits of maximum likelihood estimation for Regression and Forecasting |
8, 5, 5 |
Accept (Poster) |
1075 |
6 |
Stein Latent Optimization for Generative Adversarial Networks |
6, 6, 6, 6 |
Accept (Poster) |
1076 |
6 |
DISSECT: Disentangled Simultaneous Explanations via Concept Traversals |
6, 6, 6, 6 |
Accept (Poster) |
1077 |
6 |
Learning Symmetric Representations for Equivariant World Models |
6, 6, 6, 6 |
Reject |
1078 |
6 |
DictFormer: Tiny Transformer with Shared Dictionary |
6, 6, 6, 6 |
Accept (Poster) |
1079 |
6 |
Complete Verification via Multi-Neuron Relaxation Guided Branch-and-Bound |
6, 6, 6, 6, 6 |
Accept (Poster) |
1080 |
6 |
Augmented Sliced Wasserstein Distances |
6, 6, 6, 6 |
Accept (Poster) |
1081 |
6 |
Top-label calibration and multiclass-to-binary reductions |
5, 8, 5, 6 |
Accept (Poster) |
1082 |
6 |
Adversarial Unlearning of Backdoors via Implicit Hypergradient |
6, 6, 6, 6 |
Accept (Poster) |
1083 |
6 |
Scaling the Depth of Vision Transformers via the Fourier Domain Analysis |
6, 6, 6 |
Accept (Poster) |
1084 |
6 |
W-CTC: a Connectionist Temporal Classification Loss with Wild Cards |
6, 6, 6, 6 |
Accept (Poster) |
1085 |
6 |
Prototype memory and attention mechanisms for few shot image generation |
5, 5, 8 |
Accept (Poster) |
1086 |
6 |
Discrepancy-Based Active Learning for Domain Adaptation |
6, 6, 6, 6 |
Accept (Poster) |
1087 |
6 |
Illiterate DALL$\cdot$E Learns to Compose |
6, 6, 6 |
Accept (Poster) |
1088 |
6 |
Multi-Objective Online Learning |
6, 6, 6, 6 |
Reject |
1089 |
6 |
Nonlinear ICA Using Volume-Preserving Transformations |
6, 6, 6, 6, 6 |
Accept (Poster) |
1090 |
6 |
SplitRegex: Faster Regex Synthesis via Neural Example Splitting |
8, 6, 5, 5 |
Reject |
1091 |
6 |
Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlation |
6, 6, 6 |
Accept (Poster) |
1092 |
6 |
Trading Coverage for Precision: Conformal Prediction with Limited False Discoveries |
6, 6, 6, 6 |
Reject |
1093 |
6 |
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning |
8, 5, 5 |
Reject |
1094 |
6 |
Pseudo Numerical Methods for Diffusion Models on Manifolds |
6, 5, 8, 5 |
Accept (Poster) |
1095 |
6 |
PoNet: Pooling Network for Efficient Token Mixing in Long Sequences |
8, 5, 6, 5 |
Accept (Poster) |
1096 |
6 |
FILM: Following Instructions in Language with Modular Methods |
6, 6, 6, 6 |
Accept (Poster) |
1097 |
6 |
Learning Representation from Neural Fisher Kernel with Low-rank Approximation |
6, 6, 6 |
Accept (Poster) |
1098 |
5.83 |
Generalisation in Lifelong Reinforcement Learning through Logical Composition |
6, 6, 8, 5, 5, 5 |
Accept (Poster) |
1099 |
5.8 |
Mean-Variance Efficient Reinforcement Learning by Expected Quadratic Utility Maximization |
5, 5, 6, 8, 5 |
Reject |
1100 |
5.8 |
Why Propagate Alone? Parallel Use of Labels and Features on Graphs |
8, 6, 5, 5, 5 |
Accept (Poster) |
1101 |
5.8 |
Data Efficient Language-Supervised Zero-Shot Recognition with Optimal Transport Distillation |
6, 6, 6, 6, 5 |
Accept (Poster) |
1102 |
5.8 |
Graph-based Nearest Neighbor Search in Hyperbolic Spaces |
5, 6, 6, 6, 6 |
Accept (Poster) |
1103 |
5.8 |
Symbolic Learning to Optimize: Towards Interpretability and Scalability |
6, 6, 5, 6, 6 |
Accept (Poster) |
1104 |
5.8 |
Relational Learning with Variational Bayes |
6, 6, 6, 6, 5 |
Accept (Poster) |
1105 |
5.8 |
Self-Supervised Prime-Dual Networks for Few-Shot Image Classification |
6, 6, 6, 5, 6 |
Reject |
1106 |
5.8 |
Amortized Implicit Differentiation for Stochastic Bilevel Optimization |
6, 8, 6, 6, 3 |
Accept (Poster) |
1107 |
5.8 |
Regularized Autoencoders for Isometric Representation Learning |
5, 8, 5, 5, 6 |
Accept (Poster) |
1108 |
5.8 |
Mixed-Memory RNNs for Learning Long-term Dependencies in Irregularly Sampled Time Series |
8, 8, 3, 5, 5 |
Reject |
1109 |
5.8 |
A Generalized Weighted Optimization Method for Computational Learning and Inversion |
6, 6, 5, 6, 6 |
Accept (Poster) |
1110 |
5.75 |
Gating Mechanisms Underlying Sequence-to-Sequence Working Memory |
6, 3, 6, 8 |
Reject |
1111 |
5.75 |
Adaptive Filters for Low-Latency and Memory-Efficient Graph Neural Networks |
3, 6, 6, 8 |
Accept (Poster) |
1112 |
5.75 |
Task-Induced Representation Learning |
6, 6, 6, 5 |
Accept (Poster) |
1113 |
5.75 |
RMNet: Equivalently Removing Residual Connection from Networks |
3, 6, 6, 8 |
Reject |
1114 |
5.75 |
Why Should I Trust You, Bellman? Evaluating the Bellman Objective with Off-Policy Data |
3, 6, 8, 6 |
Reject |
1115 |
5.75 |
Contrastive Attraction and Contrastive Repulsion for Representation Learning |
8, 3, 6, 6 |
Reject |
1116 |
5.75 |
GLASS: GNN with Labeling Tricks for Subgraph Representation Learning |
6, 6, 6, 5 |
Accept (Poster) |
1117 |
5.75 |
PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration |
6, 5, 6, 6 |
Reject |
1118 |
5.75 |
Accelerating Training of Deep Spiking Neural Networks with Parameter Initialization |
6, 5, 6, 6 |
Reject |
1119 |
5.75 |
A Sampling-Free Approximation of Gaussian Variational Auto-Encoders |
8, 5, 5, 5 |
Reject |
1120 |
5.75 |
Learn Locally, Correct Globally: A Distributed Algorithm for Training Graph Neural Networks |
5, 6, 6, 6 |
Accept (Poster) |
1121 |
5.75 |
A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Model |
3, 6, 8, 6 |
Accept (Poster) |
1122 |
5.75 |
Optimization inspired Multi-Branch Equilibrium Models |
6, 5, 6, 6 |
Accept (Poster) |
1123 |
5.75 |
On the Importance of Difficulty Calibration in Membership Inference Attacks |
5, 5, 8, 5 |
Accept (Poster) |
1124 |
5.75 |
Focus on the Common Good: Group Distributional Robustness Follows |
6, 3, 6, 8 |
Accept (Poster) |
1125 |
5.75 |
Expressiveness of Neural Networks Having Width Equal or Below the Input Dimension |
6, 6, 5, 6 |
Reject |
1126 |
5.75 |
Blurs Make Results Clearer: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness |
5, 5, 8, 5 |
Reject |
1127 |
5.75 |
CodeTrek: Flexible Modeling of Code using an Extensible Relational Representation |
8, 5, 5, 5 |
Accept (Poster) |
1128 |
5.75 |
Accelerating Stochastic Simulation with Interactive Neural Processes |
6, 5, 6, 6 |
Reject |
1129 |
5.75 |
Hierarchical Cross Contrastive Learning of Visual Representations |
6, 5, 6, 6 |
Reject |
1130 |
5.75 |
A Zest of LIME: Towards Architecture-Independent Model Distances |
3, 8, 6, 6 |
Accept (Poster) |
1131 |
5.75 |
A Comparison of Variable Selection Methods for Blockwise Diagonal Designs |
8, 3, 6, 6 |
Accept (Poster) |
1132 |
5.75 |
Layer-wise Adaptive Model Aggregation for Scalable Federated Learning |
5, 5, 5, 8 |
Reject |
1133 |
5.75 |
Convergence Analysis and Implicit Regularization of Feedback Alignment for Deep Linear Networks |
5, 5, 8, 5 |
Reject |
1134 |
5.75 |
An Information Fusion Approach to Learning with Instance-Dependent Label Noise |
5, 5, 5, 8 |
Accept (Poster) |
1135 |
5.75 |
ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks |
6, 6, 6, 5 |
Reject |
1136 |
5.75 |
Revisiting Virtual Nodes in Graph Neural Networks for Link Prediction |
6, 5, 6, 6 |
Reject |
1137 |
5.75 |
PRIMA: Planner-Reasoner Inside a Multi-task Reasoning Agent |
5, 6, 6, 6 |
Reject |
1138 |
5.75 |
Local Patch AutoAugment with Multi-Agent Collaboration |
6, 5, 6, 6 |
Reject |
1139 |
5.75 |
KL Guided Domain Adaptation |
6, 3, 8, 6 |
Accept (Poster) |
1140 |
5.75 |
Robust and Data-efficient Q-learning by Composite Value-estimation |
5, 8, 5, 5 |
Unknown |
1141 |
5.75 |
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity |
5, 6, 6, 6 |
Accept (Poster) |
1142 |
5.75 |
Neural Energy Minimization for Molecular Conformation Optimization |
3, 6, 6, 8 |
Accept (Poster) |
1143 |
5.75 |
Curriculum Learning: A Regularization Method for Efficient and Stable Billion-Scale GPT Model Pre-Training |
5, 8, 5, 5 |
Reject |
1144 |
5.75 |
Gradient-Guided Importance Sampling for Learning Discrete Energy-Based Models |
6, 6, 6, 5 |
Reject |
1145 |
5.75 |
FILIP: Fine-grained Interactive Language-Image Pre-Training |
6, 6, 5, 6 |
Accept (Poster) |
1146 |
5.75 |
Few-shot Learning with Big Prototypes |
6, 5, 6, 6 |
Reject |
1147 |
5.75 |
TAG: Task-based Accumulated Gradients for Lifelong learning |
5, 8, 5, 5 |
Reject |
1148 |
5.75 |
Towards Continual Knowledge Learning of Language Models |
3, 6, 6, 8 |
Accept (Poster) |
1149 |
5.75 |
PhaseFool: Phase-oriented Audio Adversarial Examples via Energy Dissipation |
5, 5, 5, 8 |
Reject |
1150 |
5.75 |
Dense Gaussian Processes for Few-Shot Segmentation |
5, 6, 6, 6 |
Reject |
1151 |
5.75 |
Monotonic Improvement Guarantees under Non-stationarity for Decentralized PPO |
8, 6, 6, 3 |
Reject |
1152 |
5.75 |
Acceleration of Federated Learning with Alleviated Forgetting in Local Training |
6, 5, 6, 6 |
Accept (Poster) |
1153 |
5.75 |
Towards Distribution Shift of Node-Level Prediction on Graphs: An Invariance Perspective |
6, 6, 6, 5 |
Accept (Poster) |
1154 |
5.75 |
Network Augmentation for Tiny Deep Learning |
3, 8, 6, 6 |
Accept (Poster) |
1155 |
5.75 |
Representation Disentanglement in Generative Models with Contrastive Learning |
5, 5, 5, 8 |
Reject |
1156 |
5.75 |
To Smooth or not to Smooth? On Compatibility between Label Smoothing and Knowledge Distillation |
6, 6, 6, 5 |
Unknown |
1157 |
5.75 |
LARGE: Latent-Based Regression through GAN Semantics |
5, 8, 5, 5 |
Unknown |
1158 |
5.75 |
SeqPATE: Differentially Private Text Generation via Knowledge Distillation |
6, 3, 6, 8 |
Reject |
1159 |
5.75 |
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning |
6, 3, 8, 6 |
Accept (Poster) |
1160 |
5.75 |
Variational oracle guiding for reinforcement learning |
6, 6, 3, 8 |
Accept (Poster) |
1161 |
5.75 |
Learning Synthetic Environments and Reward Networks for Reinforcement Learning |
6, 8, 3, 6 |
Accept (Poster) |
1162 |
5.75 |
Learning Generalizable Representations for Reinforcement Learning via Adaptive Meta-learner of Behavioral Similarities |
6, 6, 5, 6 |
Accept (Poster) |
1163 |
5.75 |
HALP: Hardware-Aware Latency Pruning |
5, 6, 6, 6 |
Reject |
1164 |
5.75 |
Loss Function Learning for Domain Generalization by Implicit Gradient |
6, 6, 3, 8 |
Reject |
1165 |
5.75 |
Ada-NETS: Face Clustering via Adaptive Neighbour Discovery in the Structure Space |
6, 8, 3, 6 |
Accept (Poster) |
1166 |
5.75 |
Data Poisoning Won’t Save You From Facial Recognition |
8, 6, 8, 1 |
Accept (Poster) |
1167 |
5.75 |
Constructing Orthogonal Convolutions in an Explicit Manner |
6, 3, 6, 8 |
Accept (Poster) |
1168 |
5.75 |
Fair Node Representation Learning via Adaptive Data Augmentation |
6, 8, 6, 3 |
Reject |
1169 |
5.75 |
Learning Symmetric Locomotion using Cumulative Fatigue for Reinforcement Learning |
6, 5, 6, 6 |
Reject |
1170 |
5.75 |
What Doesn't Kill You Makes You Robust(er): How to Adversarially Train against Data Poisoning |
6, 3, 8, 6 |
Reject |
1171 |
5.75 |
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework |
8, 6, 3, 6 |
Reject |
1172 |
5.75 |
Provable Adaptation across Multiway Domains via Representation Learning |
6, 8, 3, 6 |
Accept (Poster) |
1173 |
5.75 |
A Closer Look at Smoothness in Domain Adversarial Training |
5, 5, 5, 8 |
Reject |
1174 |
5.75 |
Degradation Attacks on Certifiably Robust Neural Networks |
6, 6, 5, 6 |
Reject |
1175 |
5.75 |
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees |
3, 6, 6, 8 |
Accept (Poster) |
1176 |
5.75 |
Calibration Regularized Training of Deep Neural Networks using Kernel Density Estimation |
8, 5, 5, 5 |
Reject |
1177 |
5.75 |
ConFeSS: A Framework for Single Source Cross-Domain Few-Shot Learning |
5, 6, 6, 6 |
Accept (Poster) |
1178 |
5.75 |
Variational Neural Cellular Automata |
5, 8, 5, 5 |
Accept (Poster) |
1179 |
5.75 |
Decentralized Cooperative Multi-Agent Reinforcement Learning with Exploration |
6, 8, 6, 3 |
Reject |
1180 |
5.75 |
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation |
6, 5, 6, 6 |
Reject |
1181 |
5.75 |
Diverse Client Selection for Federated Learning via Submodular Maximization |
6, 3, 6, 8 |
Accept (Poster) |
1182 |
5.75 |
Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamics |
6, 6, 6, 5 |
Reject |
1183 |
5.75 |
DKM: Differentiable k-Means Clustering Layer for Neural Network Compression |
6, 5, 6, 6 |
Accept (Poster) |
1184 |
5.75 |
Exploring extreme parameter compression for pre-trained language models |
6, 5, 6, 6 |
Accept (Poster) |
1185 |
5.75 |
Sample-efficient actor-critic algorithms with an etiquette for zero-sum Markov games |
6, 6, 6, 5 |
Reject |
1186 |
5.75 |
Self-consistent Gradient-like Eigen Decomposition in Solving Schrödinger Equations |
5, 5, 5, 8 |
Reject |
1187 |
5.75 |
Implicit Bias of Linear Equivariant Networks |
6, 5, 6, 6 |
Reject |
1188 |
5.75 |
Estimating and Penalizing Induced Preference Shifts in Recommender Systems |
6, 5, 6, 6 |
Reject |
1189 |
5.75 |
From Intervention to Domain Transportation: A Novel Perspective to Optimize Recommendation |
6, 6, 6, 5 |
Accept (Poster) |
1190 |
5.75 |
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning |
6, 5, 6, 6 |
Reject |
1191 |
5.75 |
GradMax: Growing Neural Networks using Gradient Information |
6, 6, 6, 5 |
Accept (Poster) |
1192 |
5.75 |
Surprise Minimizing Multi-Agent Learning with Energy-based Models |
6, 6, 5, 6 |
Reject |
1193 |
5.75 |
Stability based Generalization Bounds for Exponential Family Langevin Dynamics |
8, 5, 5, 5 |
Reject |
1194 |
5.75 |
Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations |
6, 6, 6, 5 |
Accept (Poster) |
1195 |
5.75 |
Self-Supervise, Refine, Repeat: Improving Unsupervised Anomaly Detection |
5, 6, 6, 6 |
Reject |
1196 |
5.75 |
SPARK: co-exploring model SPArsity and low-RanKness for compact neural networks |
6, 8, 3, 6 |
Reject |
1197 |
5.75 |
The Infinite Contextual Graph Markov Model |
5, 8, 5, 5 |
Reject |
1198 |
5.75 |
QUERY-EFFICIENT DECISION-BASED SPARSE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS |
6, 6, 6, 5 |
Accept (Poster) |
1199 |
5.75 |
Reducing the Teacher-Student Gap via Adaptive Temperatures |
6, 6, 6, 5 |
Reject |
1200 |
5.75 |
Graph Condensation for Graph Neural Networks |
6, 6, 5, 6 |
Accept (Poster) |
1201 |
5.75 |
Permutation Compressors for Provably Faster Distributed Nonconvex Optimization |
6, 6, 5, 6 |
Accept (Poster) |
1202 |
5.75 |
Distributionally Robust Fair Principal Components via Geodesic Descents |
5, 6, 6, 6 |
Accept (Poster) |
1203 |
5.75 |
On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning |
6, 6, 5, 6 |
Accept (Poster) |
1204 |
5.75 |
On the Unreasonable Effectiveness of Feature Propagation in Learning on Graphs with Missing Node Features |
5, 5, 5, 8 |
Reject |
1205 |
5.75 |
Understanding approximate and unrolled dictionary learning for pattern recovery |
8, 6, 6, 3 |
Accept (Poster) |
1206 |
5.75 |
Double Descent in Adversarial Training: An Implicit Label Noise Perspective |
6, 6, 5, 6 |
Reject |
1207 |
5.75 |
What to expect of hardware metric predictors in NAS |
6, 5, 6, 6 |
Reject |
1208 |
5.75 |
Learning a subspace of policies for online adaptation in Reinforcement Learning |
3, 6, 6, 8 |
Accept (Poster) |
1209 |
5.75 |
Constrained Physical-Statistics Models for Dynamical System Identification and Prediction |
6, 6, 8, 3 |
Accept (Poster) |
1210 |
5.75 |
How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models |
6, 6, 3, 8 |
Reject |
1211 |
5.75 |
Transformed CNNs: recasting pre-trained convolutional layers with self-attention |
5, 6, 6, 6 |
Reject |
1212 |
5.75 |
Clustered Task-Aware Meta-Learning by Learning from Learning Paths |
6, 6, 5, 6 |
Reject |
1213 |
5.75 |
Invariance Through Inference |
6, 6, 5, 6 |
Reject |
1214 |
5.75 |
Learning to Give Checkable Answers with Prover-Verifier Games |
6, 5, 6, 6 |
Reject |
1215 |
5.75 |
Generalized Demographic Parity for Group Fairness |
6, 6, 6, 5 |
Accept (Poster) |
1216 |
5.75 |
Contextual Multi-Armed Bandit with Communication Constraints |
5, 6, 6, 6 |
Reject |
1217 |
5.75 |
Implicit Regularization of Bregman Proximal Point Algorithm and Mirror Descent on Separable Data |
5, 6, 6, 6 |
Reject |
1218 |
5.75 |
Only tails matter: Average-Case Universality and Robustness in the Convex Regime |
5, 8, 5, 5 |
Reject |
1219 |
5.75 |
Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems |
8, 5, 5, 5 |
Accept (Poster) |
1220 |
5.75 |
Disentangling deep neural networks with rectified linear units using duality |
5, 6, 6, 6 |
Reject |
1221 |
5.75 |
Evaluating Language-biased image classification based on semantic compositionality |
6, 6, 8, 3 |
Accept (Poster) |
1222 |
5.75 |
Towards Building A Group-based Unsupervised Representation Disentanglement Framework |
8, 6, 3, 6 |
Accept (Poster) |
1223 |
5.75 |
One Objective for All Models --- Self-supervised Learning for Topic Models |
6, 5, 6, 6 |
Reject |
1224 |
5.75 |
Imitation Learning by Reinforcement Learning |
5, 6, 6, 6 |
Accept (Poster) |
1225 |
5.75 |
k-Median Clustering via Metric Embedding: Towards Better Initialization with Privacy |
6, 6, 6, 5 |
Reject |
1226 |
5.75 |
Blessing of Class Diversity in Pre-training |
6, 6, 8, 3 |
Reject |
1227 |
5.75 |
Locally Invariant Explanations: Towards Causal Explanations through Local Invariant Learning |
5, 8, 5, 5 |
Reject |
1228 |
5.75 |
Action-Sufficient State Representation Learning for Control with Structural Constraints |
5, 5, 5, 8 |
Reject |
1229 |
5.75 |
Towards Model Agnostic Federated Learning Using Knowledge Distillation |
6, 6, 8, 3 |
Accept (Poster) |
1230 |
5.75 |
Fully Online Meta-Learning Without Task Boundaries |
6, 6, 6, 5 |
Reject |
1231 |
5.75 |
Spectral Multiplicity Entails Sample-wise Multiple Descent |
8, 6, 6, 3 |
Reject |
1232 |
5.75 |
Did I do that? Blame as a means to identify controlled effects in reinforcement learning |
6, 5, 6, 6 |
Reject |
1233 |
5.75 |
Knowledge is reward: Learning optimal exploration by predictive reward cashing |
8, 5, 5, 5 |
Unknown |
1234 |
5.75 |
Bandit Learning with Joint Effect of Incentivized Sampling, Delayed Sampling Feedback, and Self-Reinforcing User Preferences |
6, 6, 5, 6 |
Accept (Poster) |
1235 |
5.75 |
Learning Visual-Linguistic Adequacy, Fidelity, and Fluency for Novel Object Captioning |
6, 6, 6, 5 |
Reject |
1236 |
5.75 |
Complex Locomotion Skill Learning via Differentiable Physics |
6, 6, 6, 5 |
Reject |
1237 |
5.75 |
On Margin Maximization in Linear and ReLU Networks |
5, 6, 6, 6 |
Reject |
1238 |
5.75 |
Reward Uncertainty for Exploration in Preference-based Reinforcement Learning |
5, 6, 6, 6 |
Accept (Poster) |
1239 |
5.75 |
Test-Time Adaptation to Distribution Shifts by Confidence Maximization and Input Transformation |
6, 6, 5, 6 |
Reject |
1240 |
5.75 |
Robust Unlearnable Examples: Protecting Data Privacy Against Adversarial Learning |
6, 3, 6, 8 |
Accept (Poster) |
1241 |
5.75 |
Low Entropy Deep Networks |
5, 8, 5, 5 |
Reject |
1242 |
5.75 |
Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning |
5, 6, 6, 6 |
Accept (Poster) |
1243 |
5.75 |
Exploring Non-Contrastive Representation Learning for Deep Clustering |
6, 3, 6, 8 |
Reject |
1244 |
5.75 |
Rethinking Supervised Pre-Training for Better Downstream Transferring |
6, 5, 6, 6 |
Accept (Poster) |
1245 |
5.75 |
Towards Empirical Sandwich Bounds on the Rate-Distortion Function |
6, 8, 6, 3 |
Accept (Poster) |
1246 |
5.75 |
Meaningfully Explaining Model Mistakes Using Conceptual Counterfactuals |
6, 6, 6, 5 |
Reject |
1247 |
5.75 |
Audio Lottery: Speech Recognition Made Ultra-Lightweight, Noise-Robust, and Transferable |
6, 5, 6, 6 |
Accept (Poster) |
1248 |
5.75 |
Geometric Transformers for Protein Interface Contact Prediction |
6, 6, 5, 6 |
Accept (Poster) |
1249 |
5.75 |
Online graph nets |
5, 6, 6, 6 |
Unknown |
1250 |
5.75 |
$f$-Mutual Information Contrastive Learning |
5, 6, 6, 6 |
Reject |
1251 |
5.75 |
Bounding Membership Inference |
6, 8, 6, 3 |
Reject |
1252 |
5.75 |
Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding |
5, 5, 8, 5 |
Reject |
1253 |
5.75 |
Sound Source Detection from Raw Waveforms with Multi-Scale Synperiodic Filterbanks |
6, 5, 6, 6 |
Reject |
1254 |
5.75 |
FP-DETR: Detection Transformer Advanced by Fully Pre-training |
6, 6, 6, 5 |
Accept (Poster) |
1255 |
5.75 |
Learning Audio-Visual Dereverberation |
6, 3, 6, 8 |
Reject |
1256 |
5.75 |
Should We Be Pre-training? An Argument for End-task Aware Training as an Alternative |
6, 6, 6, 5 |
Accept (Poster) |
1257 |
5.75 |
Stabilized Likelihood-based Imitation Learning via Denoising Continuous Normalizing Flow |
5, 5, 8, 5 |
Reject |
1258 |
5.75 |
$\alpha$-Weighted Federated Adversarial Training |
8, 5, 5, 5 |
Reject |
1259 |
5.67 |
Style Equalization: Unsupervised Learning of Controllable Generative Sequence Models |
8, 6, 3 |
Reject |
1260 |
5.67 |
Structural Causal Interpretation Theorem |
6, 3, 8 |
Reject |
1261 |
5.67 |
Modelling neuronal behaviour with time series regression: Recurrent Neural Networks on synthetic C. elegans data |
6, 3, 8 |
Reject |
1262 |
5.67 |
MANDERA: Malicious Node Detection in Federated Learning via Ranking |
6, 8, 3 |
Reject |
1263 |
5.67 |
Distributional Perturbation for Efficient Exploration in Distributional Reinforcement Learning |
6, 5, 6 |
Reject |
1264 |
5.67 |
Neural Spectral Marked Point Processes |
6, 8, 3 |
Accept (Poster) |
1265 |
5.67 |
The Power of Contrast for Feature Learning: A Theoretical Analysis |
6, 6, 5 |
Reject |
1266 |
5.67 |
Multi-Domain Self-Supervised Learning |
6, 6, 5 |
Reject |
1267 |
5.67 |
ScaLA: Speeding-Up Fine-tuning of Pre-trained Transformer Networks via Efficient and Scalable Adversarial Perturbation |
5, 6, 6 |
Reject |
1268 |
5.67 |
Reinforcement Learning with Efficient Active Feature Acquisition |
5, 6, 6 |
Reject |
1269 |
5.67 |
Planckian jitter: enhancing the color quality of self-supervised visual representations |
6, 5, 6 |
Reject |
1270 |
5.67 |
Deep Reinforcement Learning for Equal Risk Option Pricing and Hedging under Dynamic Expectile Risk Measures |
5, 6, 6 |
Reject |
1271 |
5.67 |
PARS: PSEUDO-LABEL AWARE ROBUST SAMPLE SELECTION FOR LEARNING WITH NOISY LABELS |
6, 5, 6 |
Reject |
1272 |
5.67 |
ZeroFL: Efficient On-Device Training for Federated Learning with Local Sparsity |
6, 6, 5 |
Accept (Poster) |
1273 |
5.67 |
Decentralized Learning for Overparameterized Problems: A Multi-Agent Kernel Approximation Approach |
6, 5, 6 |
Accept (Poster) |
1274 |
5.67 |
Graph-Relational Domain Adaptation |
6, 5, 6 |
Accept (Poster) |
1275 |
5.67 |
Demystifying Batch Normalization in ReLU Networks: Equivalent Convex Optimization Models and Implicit Regularization |
5, 6, 6 |
Accept (Poster) |
1276 |
5.67 |
Boundary-aware Pre-training for Video Scene Segmentation |
5, 6, 6 |
Reject |
1277 |
5.67 |
R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning |
5, 6, 6 |
Accept (Spotlight) |
1278 |
5.67 |
NAFS: A Simple yet Tough-to-Beat Baseline for Graph Representation Learning |
6, 6, 5 |
Reject |
1279 |
5.67 |
Metrics Matter: A Closer Look on Self-Paced Reinforcement Learning |
6, 5, 6 |
Reject |
1280 |
5.67 |
Towards Understanding the Data Dependency of Mixup-style Training |
3, 8, 6 |
Accept (Spotlight) |
1281 |
5.67 |
A Closer Look at Prototype Classifier for Few-shot Image Classification |
5, 6, 6 |
Reject |
1282 |
5.67 |
Message Function Search for Hyper-relational Knowledge Graph |
6, 6, 5 |
Reject |
1283 |
5.67 |
Exploiting Class Activation Value for Partial-Label Learning |
6, 8, 3 |
Accept (Poster) |
1284 |
5.67 |
Graph Kernel Neural Networks |
6, 6, 5 |
Reject |
1285 |
5.67 |
Imitation Learning from Observations under Transition Model Disparity |
5, 6, 6 |
Accept (Poster) |
1286 |
5.67 |
Hierarchically Regularized Deep Forecasting |
6, 5, 6 |
Reject |
1287 |
5.67 |
Shift-tolerant Perceptual Similarity Metric |
3, 8, 6 |
Reject |
1288 |
5.67 |
Automatic Termination for Hyperparameter Optimization |
6, 5, 6 |
Reject |
1289 |
5.67 |
Learning Sample Reweighting for Adversarial Robustness |
3, 3, 8, 6, 6, 8 |
Reject |
1290 |
5.67 |
Feature Flow Regularization: Improving Structured Sparsity in Deep Neural Networks |
6, 6, 5 |
Reject |
1291 |
5.67 |
Meta Learning Low Rank Covariance Factors for Energy Based Deterministic Uncertainty |
6, 5, 6 |
Accept (Poster) |
1292 |
5.67 |
Learning Stochastic Shortest Path with Linear Function Approximation |
5, 6, 6 |
Reject |
1293 |
5.67 |
Empirical Study of the Decision Region and Robustness in Deep Neural Networks |
5, 6, 6 |
Reject |
1294 |
5.67 |
Task Affinity with Maximum Bipartite Matching in Few-Shot Learning |
3, 8, 6 |
Accept (Poster) |
1295 |
5.67 |
Iterated Reasoning with Mutual Information in Cooperative and Byzantine Decentralized Teaming |
3, 6, 8 |
Accept (Poster) |
1296 |
5.67 |
Gradient play in stochastic games: stationary points, convergence, and sample complexity |
8, 6, 3 |
Reject |
1297 |
5.67 |
Learning to Generalize Compositionally by Transferring Across Semantic Parsing Tasks |
5, 6, 6 |
Reject |
1298 |
5.67 |
Practical and Private Heterogeneous Federated Learning |
6, 6, 5 |
Reject |
1299 |
5.67 |
EXACT: Scalable Graph Neural Networks Training via Extreme Activation Compression |
8, 3, 6 |
Accept (Poster) |
1300 |
5.6 |
Plant 'n' Seek: Can You Find the Winning Ticket? |
6, 5, 6, 6, 5 |
Accept (Poster) |
1301 |
5.6 |
Limitations of Active Learning With Deep Transformer Language Models |
6, 6, 5, 5, 6 |
Reject |
1302 |
5.6 |
Federated Robustness Propagation: Sharing Adversarial Robustness in Federated Learning |
3, 8, 8, 6, 3 |
Reject |
1303 |
5.6 |
LASSO: Latent Sub-spaces Orientation for Domain Generalization |
6, 6, 5, 6, 5 |
Reject |
1304 |
5.6 |
Translatotron 2: Robust direct speech-to-speech translation |
6, 5, 6, 5, 6 |
Reject |
1305 |
5.6 |
Closed-form Sample Probing for Learning Generative Models in Zero-shot Learning |
5, 6, 5, 6, 6 |
Accept (Poster) |
1306 |
5.6 |
Learning shared neural manifolds from multi-subject FMRI data |
3, 6, 8, 6, 5 |
Reject |
1307 |
5.6 |
Second-Order Unsupervised Feature Selection via Knowledge Contrastive Distillation |
8, 6, 5, 3, 6 |
Reject |
1308 |
5.6 |
Understanding Knowledge Integration in Language Models with Graph Convolutions |
6, 5, 3, 6, 8 |
Reject |
1309 |
5.6 |
KNIFE: Kernelized-Neural Differential Entropy Estimation |
5, 6, 5, 6, 6 |
Reject |
1310 |
5.6 |
Mixture Representation Learning with Coupled Autoencoders |
8, 5, 5, 5, 5 |
Reject |
1311 |
5.6 |
Deep Ensemble as a Gaussian Process Posterior |
5, 8, 5, 5, 5 |
Reject |
1312 |
5.6 |
Fully Steerable 3D Spherical Neurons |
5, 5, 8, 5, 5 |
Reject |
1313 |
5.6 |
Graph Neural Network Guided Local Search for the Traveling Salesperson Problem |
8, 3, 6, 8, 3 |
Accept (Poster) |
1314 |
5.6 |
Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results |
5, 6, 6, 5, 6 |
Reject |
1315 |
5.6 |
Learning to Solve Multi-Robot Task Allocation with a Covariant-Attention based Neural Architecture |
6, 8, 6, 3, 5 |
Reject |
1316 |
5.6 |
Provably Robust Detection of Out-of-distribution Data (almost) for free |
5, 6, 6, 3, 8 |
Reject |
1317 |
5.5 |
Causal Contextual Bandits with Targeted Interventions |
6, 6, 5, 5 |
Accept (Poster) |
1318 |
5.5 |
Contrastively Enforcing Distinctiveness for Multi-Label Classification |
6, 5, 6, 5 |
Reject |
1319 |
5.5 |
Reward Learning as Doubly Nonparametric Bandits: Optimal Design and Scaling Laws |
5, 5, 6, 6 |
Reject |
1320 |
5.5 |
DEUP: Direct Epistemic Uncertainty Prediction |
6, 5, 6, 5 |
Reject |
1321 |
5.5 |
Attacking deep networks with surrogate-based adversarial black-box methods is easy |
5, 5, 6, 6 |
Accept (Poster) |
1322 |
5.5 |
Semantically Controllable Generation of Physical Scenes with Explicit Knowledge |
5, 5, 6, 6 |
Reject |
1323 |
5.5 |
Towards Understanding the Condensation of Neural Networks at Initial Training |
5, 5, 6, 6 |
Reject |
1324 |
5.5 |
Short optimization paths lead to good generalization |
6, 5, 6, 5 |
Reject |
1325 |
5.5 |
Bayesian Neural Network Priors Revisited |
6, 3, 8, 5 |
Accept (Poster) |
1326 |
5.5 |
Langevin Autoencoders for Learning Deep Latent Variable Models |
6, 6, 5, 5 |
Reject |
1327 |
5.5 |
Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning |
5, 6, 5, 6 |
Reject |
1328 |
5.5 |
Trans-Encoder: Unsupervised sentence-pair modelling through self- and mutual-distillations |
5, 6, 5, 6 |
Accept (Poster) |
1329 |
5.5 |
A Risk-Sensitive Policy Gradient Method |
6, 5, 6, 5 |
Reject |
1330 |
5.5 |
Crystal Diffusion Variational Autoencoder for Periodic Material Generation |
3, 6, 5, 8 |
Accept (Poster) |
1331 |
5.5 |
On the Implicit Biases of Architecture & Gradient Descent |
5, 6, 5, 6 |
Reject |
1332 |
5.5 |
On the relationship between disentanglement and multi-task learning |
6, 5, 6, 5 |
Reject |
1333 |
5.5 |
Divergence-Regularized Multi-Agent Actor-Critic |
6, 6, 5, 5 |
Reject |
1334 |
5.5 |
Generalization of GANs and overparameterized models under Lipschitz continuity |
6, 8, 5, 3 |
Reject |
1335 |
5.5 |
How to train RNNs on chaotic data? |
6, 5, 6, 5 |
Reject |
1336 |
5.5 |
Uncertainty-Aware Deep Video Compression with Ensembles |
5, 6, 5, 6 |
Reject |
1337 |
5.5 |
Prioritized training on points that are learnable, worth learning, and not yet learned |
5, 5, 6, 6 |
Reject |
1338 |
5.5 |
Balancing Average and Worst-case Accuracy in Multitask Learning |
5, 6, 5, 6 |
Reject |
1339 |
5.5 |
Search Spaces for Neural Model Training |
5, 5, 6, 6 |
Reject |
1340 |
5.5 |
Non-Linear Operator Approximations for Initial Value Problems |
6, 3, 5, 8 |
Accept (Poster) |
1341 |
5.5 |
Re-evaluating Word Mover's Distance |
8, 8, 3, 3 |
Reject |
1342 |
5.5 |
Tuformer: Data-Driven Design of Expressive Transformer by Tucker Tensor Representation |
5, 6, 6, 5 |
Accept (Poster) |
1343 |
5.5 |
Explanatory Learning: Beyond Empiricism in Neural Networks |
5, 8, 3, 6 |
Reject |
1344 |
5.5 |
Representation mitosis in wide neural networks |
6, 5, 5, 6 |
Reject |
1345 |
5.5 |
Reasoning-Modulated Representations |
6, 5, 5, 6 |
Reject |
1346 |
5.5 |
Dynamic Token Normalization improves Vision Transformers |
5, 5, 6, 6 |
Accept (Poster) |
1347 |
5.5 |
Stability Regularization for Discrete Representation Learning |
5, 5, 6, 6 |
Accept (Poster) |
1348 |
5.5 |
Towards Federated Learning on Time-Evolving Heterogeneous Data |
8, 3, 8, 3 |
Reject |
1349 |
5.5 |
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability |
5, 6, 6, 5 |
Reject |
1350 |
5.5 |
Inverse Contextual Bandits: Learning How Behavior Evolves over Time |
5, 6, 5, 6 |
Reject |
1351 |
5.5 |
Learning Pseudometric-based Action Representations for Offline Reinforcement Learning |
6, 5, 6, 5 |
Reject |
1352 |
5.5 |
Reducing the Communication Cost of Federated Learning through Multistage Optimization |
6, 5, 5, 6 |
Accept (Poster) |
1353 |
5.5 |
Coarformer: Transformer for large graph via graph coarsening |
3, 6, 5, 8 |
Reject |
1354 |
5.5 |
Towards General Robustness to Bad Training Data |
5, 6, 5, 6 |
Reject |
1355 |
5.5 |
Contrastive Learning is Just Meta-Learning |
6, 5, 5, 6 |
Accept (Poster) |
1356 |
5.5 |
Training Multi-Layer Over-Parametrized Neural Network in Subquadratic Time |
5, 6, 5, 6 |
Reject |
1357 |
5.5 |
Generalizable Person Re-identification Without Demographics |
6, 5, 3, 8 |
Reject |
1358 |
5.5 |
Instance-Adaptive Video Compression: Improving Neural Codecs by Training on the Test Set |
5, 6, 6, 5 |
Reject |
1359 |
5.5 |
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation |
3, 8, 6, 5 |
Reject |
1360 |
5.5 |
A Variance Reduction Method for Neural-based Divergence Estimation |
3, 3, 8, 8 |
Reject |
1361 |
5.5 |
Role Diversity Matters: A Study of Cooperative Training Strategies for Multi-Agent RL |
6, 5, 6, 5 |
Reject |
1362 |
5.5 |
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum |
5, 8, 6, 3 |
Reject |
1363 |
5.5 |
Test-time Batch Statistics Calibration for Covariate Shift |
6, 5, 5, 6 |
Reject |
1364 |
5.5 |
SAFER: Data-Efficient and Safe Reinforcement Learning Through Skill Acquisition |
5, 6, 3, 8 |
Reject |
1365 |
5.5 |
Lifting Imbalanced Regression with Self-Supervised Learning |
5, 5, 6, 6 |
Reject |
1366 |
5.5 |
Coherent and Consistent Relational Transfer Learning with Autoencoders |
8, 6, 3, 5 |
Reject |
1367 |
5.5 |
Detecting Worst-case Corruptions via Loss Landscape Curvature in Deep Reinforcement Learning |
3, 8, 3, 8 |
Reject |
1368 |
5.5 |
Towards Generic Interface for Human-Neural Network Knowledge Exchange |
6, 6, 5, 5 |
Reject |
1369 |
5.5 |
Object Pursuit: Building a Space of Objects via Discriminative Weight Generation |
5, 6, 5, 6 |
Accept (Poster) |
1370 |
5.5 |
Targeted Environment Design from Offline Data |
8, 5, 3, 6 |
Reject |
1371 |
5.5 |
Inductive Lottery Ticket Learning for Graph Neural Networks |
5, 6, 5, 6 |
Reject |
1372 |
5.5 |
Recurrent Parameter Generators |
6, 6, 5, 5 |
Reject |
1373 |
5.5 |
Gradient-based Meta-solving and Its Applications to Iterative Methods for Solving Differential Equations |
6, 5, 8, 3 |
Reject |
1374 |
5.5 |
Learning Symbolic Rules for Reasoning in Quasi-Natural Language |
3, 5, 6, 8 |
Reject |
1375 |
5.5 |
Evaluating Predictive Distributions: Does Bayesian Deep Learning Work? |
5, 6, 5, 6 |
Reject |
1376 |
5.5 |
Model Validation Using Mutated Training Labels: An Exploratory Study |
5, 8, 3, 6 |
Reject |
1377 |
5.5 |
NAIL: A Challenging Benchmark for Na"ive Logical Reasoning |
6, 8, 3, 5 |
Reject |
1378 |
5.5 |
A Frequency Perspective of Adversarial Robustness |
5, 6, 3, 8 |
Reject |
1379 |
5.5 |
New Insights on Reducing Abrupt Representation Change in Online Continual Learning |
5, 6, 8, 3 |
Accept (Poster) |
1380 |
5.5 |
Self-Contrastive Learning |
5, 6, 5, 6 |
Reject |
1381 |
5.5 |
Contrastive Learning Through Time |
5, 3, 8, 6 |
Unknown |
1382 |
5.5 |
3D Pre-training improves GNNs for Molecular Property Prediction |
6, 8, 3, 5 |
Reject |
1383 |
5.5 |
Avoiding Overfitting to the Importance Weights in Offline Policy Optimization |
5, 5, 6, 6 |
Reject |
1384 |
5.5 |
Maximum Likelihood Training of Parametrized Diffusion Model |
5, 6, 5, 6 |
Reject |
1385 |
5.5 |
Spectral Bias in Practice: the Role of Function Frequency in Generalization |
3, 8, 8, 3 |
Reject |
1386 |
5.5 |
SANE: Specialization-Aware Neural Network Ensemble |
5, 6, 5, 6 |
Reject |
1387 |
5.5 |
Learn the Time to Learn: Replay Scheduling for Continual Learning |
8, 3, 5, 6 |
Reject |
1388 |
5.5 |
Generalized Sampling Method for Few Shot Learning |
6, 6, 5, 5 |
Unknown |
1389 |
5.5 |
A Hierarchical Bayesian Approach to Inverse Reinforcement Learning with Symbolic Reward Machines |
6, 5, 5, 6 |
Reject |
1390 |
5.5 |
FED-$\chi^2$: Secure Federated Correlation Test |
6, 5, 6, 5 |
Reject |
1391 |
5.5 |
A Statistical Manifold Framework for Point Cloud Data |
3, 8, 6, 5 |
Reject |
1392 |
5.5 |
Correct-N-Contrast: a Contrastive Approach for Improving Robustness to Spurious Correlations |
6, 5, 5, 6 |
Reject |
1393 |
5.5 |
LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5 |
5, 6, 6, 5 |
Accept (Poster) |
1394 |
5.5 |
Scalable multimodal variational autoencoders with surrogate joint posterior |
3, 8, 6, 5 |
Reject |
1395 |
5.5 |
Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective |
5, 5, 6, 6 |
Reject |
1396 |
5.5 |
Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints |
6, 6, 5, 5 |
Reject |
1397 |
5.5 |
When less is more: Simplifying inputs aids neural network understanding |
6, 6, 5, 5 |
Reject |
1398 |
5.5 |
Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How |
6, 5, 5, 6 |
Accept (Poster) |
1399 |
5.5 |
On the Convergence of Shallow Neural Network Training with Randomly Masked Neurons |
6, 5, 5, 6 |
Unknown |
1400 |
5.5 |
Learning Diverse Options via InfoMax Termination Critic |
5, 5, 6, 6 |
Reject |
1401 |
5.5 |
Hierarchical Multimodal Variational Autoencoders |
5, 5, 6, 6 |
Reject |
1402 |
5.5 |
Neural tangent kernel eigenvalues accurately predict generalization |
3, 6, 5, 8 |
Reject |
1403 |
5.5 |
Fooling Adversarial Training with Induction Noise |
5, 5, 6, 6 |
Reject |
1404 |
5.5 |
Show Your Work: Scratchpads for Intermediate Computation with Language Models |
3, 8, 8, 3 |
Reject |
1405 |
5.5 |
Efficient Out-of-Distribution Detection via CVAE data Generation |
5, 5, 6, 6 |
Reject |
1406 |
5.5 |
FoveaTer: Foveated Transformer for Image Classification |
8, 3, 6, 5 |
Reject |
1407 |
5.5 |
On the Global Convergence of Gradient Descent for multi-layer ResNets in the mean-field regime |
3, 5, 6, 8 |
Reject |
1408 |
5.5 |
Learning Surface Parameterization for Document Image Unwarping |
6, 5, 6, 5 |
Reject |
1409 |
5.5 |
The Role of Pretrained Representations for the OOD Generalization of RL Agents |
8, 6, 3, 5 |
Accept (Poster) |
1410 |
5.5 |
Analyzing Populations of Neural Networks via Dynamical Model Embedding |
6, 6, 5, 5 |
Reject |
1411 |
5.5 |
Distributed Skellam Mechanism: a Novel Approach to Federated Learning with Differential Privacy |
3, 6, 5, 8 |
Reject |
1412 |
5.5 |
Losing Less: A Loss for Differentially Private Deep Learning |
6, 5, 5, 6 |
Reject |
1413 |
5.5 |
Learning State Representations via Retracing in Reinforcement Learning |
6, 3, 5, 8 |
Accept (Poster) |
1414 |
5.5 |
Deep learning via message passing algorithms based on belief propagation |
3, 6, 5, 8 |
Reject |
1415 |
5.5 |
Understanding and Leveraging Overparameterization in Recursive Value Estimation |
8, 6, 3, 5 |
Accept (Poster) |
1416 |
5.5 |
Localized Persistent Homologies for more Effective Deep Learning |
5, 3, 8, 6 |
Reject |
1417 |
5.5 |
Learning Context-Adapted Video-Text Retrieval by Attending to User Comments |
6, 5, 5, 6 |
Reject |
1418 |
5.5 |
Pretrained Language Model in Continual Learning: A Comparative Study |
3, 5, 6, 8 |
Accept (Poster) |
1419 |
5.5 |
AdaFocal: Calibration-aware Adaptive Focal Loss |
6, 5, 5, 6 |
Reject |
1420 |
5.5 |
Pre-training Molecular Graph Representation with 3D Geometry |
5, 5, 6, 6 |
Accept (Poster) |
1421 |
5.5 |
Source-Target Unified Knowledge Distillation for Memory-Efficient Federated Domain Adaptation on Edge Devices |
3, 8, 5, 6 |
Reject |
1422 |
5.5 |
Few-Shot Classification with Task-Adaptive Semantic Feature Learning |
6, 6, 5, 5 |
Reject |
1423 |
5.5 |
Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs |
5, 5, 6, 6 |
Accept (Poster) |
1424 |
5.5 |
Safe Opponent-Exploitation Subgame Refinement |
6, 5, 8, 3 |
Reject |
1425 |
5.5 |
Logarithmic Unbiased Quantization: Practical 4-bit Training in Deep Learning |
5, 6, 5, 6 |
Reject |
1426 |
5.5 |
Explaining Knowledge Graph Embedding via Latent Rule Learning |
5, 6, 6, 5 |
Unknown |
1427 |
5.5 |
KIMERA: Injecting Domain Knowledge into Vacant Transformer Heads |
5, 5, 6, 6 |
Unknown |
1428 |
5.5 |
Associated Learning: an Alternative to End-to-End Backpropagation that Works on CNN, RNN, and Transformer |
6, 6, 5, 5 |
Accept (Poster) |
1429 |
5.5 |
SLASH: Embracing Probabilistic Circuits into Neural Answer Set Programming |
6, 8, 5, 3 |
Reject |
1430 |
5.5 |
Self-supervised Models are Good Teaching Assistants for Vision Transformers |
3, 8, 8, 3 |
Unknown |
1431 |
5.5 |
CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models |
5, 5, 6, 6 |
Reject |
1432 |
5.5 |
Towards Evaluating the Robustness of Neural Networks Learned by Transduction |
5, 6, 6, 5 |
Accept (Poster) |
1433 |
5.5 |
PI3NN: Out-of-distribution-aware Prediction Intervals from Three Neural Networks |
5, 6, 5, 6 |
Accept (Poster) |
1434 |
5.5 |
Learning to Affiliate: Mutual Centralized Learning for Few-shot Classification |
5, 6, 5, 6 |
Unknown |
1435 |
5.5 |
Improved Generalization Risk Bounds for Meta-Learning with PAC-Bayes-kl Analysis |
5, 6, 6, 5 |
Unknown |
1436 |
5.5 |
Counterbalancing Teacher: Regularizing Batch Normalized Models for Robustness |
5, 3, 8, 6 |
Reject |
1437 |
5.5 |
Improving zero-shot generalization in offline reinforcement learning using generalized similarity functions |
5, 6, 6, 5 |
Reject |
1438 |
5.5 |
Tactics on Refining Decision Boundary for Improving Certification-based Robust Training |
3, 8, 5, 6 |
Reject |
1439 |
5.5 |
Distributed Optimal Margin Distribution Machine |
3, 3, 8, 8 |
Reject |
1440 |
5.5 |
Learning Algebraic Representation for Systematic Generalization in Abstract Reasoning |
5, 6, 3, 8 |
Unknown |
1441 |
5.5 |
Inductive Biases and Variable Creation in Self-Attention Mechanisms |
3, 5, 6, 8 |
Reject |
1442 |
5.5 |
Mining Multi-Label Samples from Single Positive Labels |
6, 5, 6, 5 |
Unknown |
1443 |
5.5 |
Denoising Diffusion Gamma Models |
5, 6, 5, 6 |
Reject |
1444 |
5.5 |
CARD: Certifiably Robust Machine Learning Pipeline via Domain Knowledge Integration |
6, 6, 5, 5 |
Unknown |
1445 |
5.5 |
Hinge Policy Optimization: Rethinking Policy Improvement and Reinterpreting PPO |
3, 5, 6, 8 |
Reject |
1446 |
5.5 |
Mitigating Dataset Bias Using Per-Sample Gradients From A Biased Classifier |
6, 6, 5, 5 |
Reject |
1447 |
5.5 |
Learning Multi-Objective Curricula for Deep Reinforcement Learning |
5, 6, 8, 3 |
Unknown |
1448 |
5.5 |
Burst Image Restoration and Enhancement |
6, 5, 5, 6 |
Unknown |
1449 |
5.5 |
Rethinking Temperature in Graph Contrastive Learning |
6, 5, 3, 8 |
Reject |
1450 |
5.5 |
DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck |
5, 5, 6, 6 |
Reject |
1451 |
5.5 |
On Reward Maximization and Distribution Matching for Fine-Tuning Language Models |
5, 6, 5, 6 |
Reject |
1452 |
5.5 |
Intra-class Mixup for Out-of-Distribution Detection |
6, 8, 5, 3 |
Reject |
1453 |
5.5 |
LatentKeypointGAN: Controlling GANs via Latent Keypoints |
6, 5, 6, 5 |
Reject |
1454 |
5.5 |
Diurnal or Nocturnal? Federated Learning of Multi-branch Networks from Periodically Shifting Distributions |
3, 6, 5, 8 |
Accept (Poster) |
1455 |
5.5 |
FLOAT: FAST LEARNABLE ONCE-FOR-ALL ADVERSARIAL TRAINING FOR TUNABLE TRADE-OFF BETWEEN ACCURACY AND ROBUSTNESS |
3, 8, 5, 6 |
Reject |
1456 |
5.5 |
Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification |
6, 6, 5, 5 |
Reject |
1457 |
5.5 |
Measuring the Interpretability of Unsupervised Representations via Quantized Reversed Probing |
8, 5, 3, 6 |
Accept (Poster) |
1458 |
5.5 |
Deep Representations for Time-varying Brain Datasets |
5, 6, 6, 5 |
Reject |
1459 |
5.5 |
Multi-Task Neural Processes |
6, 5, 5, 6 |
Reject |
1460 |
5.5 |
Learning to Guide and to be Guided in the Architect-Builder Problem |
3, 6, 8, 5 |
Accept (Poster) |
1461 |
5.5 |
Auto-Encoding Inverse Reinforcement Learning |
6, 8, 3, 5 |
Reject |
1462 |
5.5 |
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks |
6, 6, 5, 5 |
Accept (Poster) |
1463 |
5.5 |
On Heterogeneously Distributed Data, Sparsity Matters |
6, 6, 5, 5 |
Reject |
1464 |
5.5 |
Thompson Sampling for (Combinatorial) Pure Exploration |
6, 6, 5, 5 |
Reject |
1465 |
5.5 |
Retrieval-Augmented Reinforcement Learning |
6, 5, 5, 6 |
Reject |
1466 |
5.5 |
Calibrated ensembles - a simple way to mitigate ID-OOD accuracy tradeoffs |
6, 5, 5, 6 |
Reject |
1467 |
5.5 |
Scaling Fair Learning to Hundreds of Intersectional Groups |
5, 5, 6, 6 |
Reject |
1468 |
5.5 |
Self-Supervised Representation Learning via Latent Graph Prediction |
6, 5, 6, 5 |
Reject |
1469 |
5.5 |
Head2Toe: Utilizing Intermediate Representations for Better OOD Generalization |
6, 5, 5, 6 |
Reject |
1470 |
5.5 |
Efficient representations for privacy-preserving inference |
5, 3, 6, 8 |
Reject |
1471 |
5.5 |
First-Order Optimization Inspired from Finite-Time Convergent Flows |
5, 6, 5, 6 |
Reject |
1472 |
5.5 |
An evaluation of quality and robustness of smoothed explanations |
6, 5, 6, 5 |
Reject |
1473 |
5.5 |
Restricted Category Removal from Model Representations using Limited Data |
5, 5, 6, 6 |
Reject |
1474 |
5.5 |
On Learning to Solve Cardinality Constrained Combinatorial Optimization in One-Shot: A Re-parameterization Approach via Gumbel-Sinkhorn-TopK |
6, 5, 6, 5 |
Reject |
1475 |
5.5 |
Constrained Density Matching and Modeling for Effective Contextualized Alignment |
6, 3, 8, 5 |
Reject |
1476 |
5.5 |
Neural Bootstrapping Attention for Neural Processes |
6, 5, 6, 5 |
Reject |
1477 |
5.5 |
ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models |
5, 6, 5, 6 |
Accept (Poster) |
1478 |
5.5 |
Learning and controlling the source-filter representation of speech with a variational autoencoder |
6, 5, 5, 6 |
Reject |
1479 |
5.5 |
Representation-Agnostic Shape Fields |
6, 5, 6, 5 |
Accept (Poster) |
1480 |
5.5 |
Convolutional Neural Network Dynamics: A Graph Perspective |
8, 6, 5, 3 |
Reject |
1481 |
5.5 |
Privacy Protected Multi-Domain Collaborative Learning |
5, 6, 6, 5 |
Unknown |
1482 |
5.5 |
Stochastic Reweighted Gradient Descent |
6, 5, 5, 6 |
Reject |
1483 |
5.5 |
No Shifted Augmentations (NSA): strong baselines for self-supervised Anomaly Detection |
5, 5, 6, 6 |
Reject |
1484 |
5.5 |
Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation |
3, 5, 6, 8 |
Accept (Poster) |
1485 |
5.5 |
Multi-Agent Reinforcement Learning with Shared Resource in Inventory Management |
6, 5, 5, 6 |
Reject |
1486 |
5.5 |
Second-Order Rewards For Successor Features |
6, 5, 5, 6 |
Reject |
1487 |
5.5 |
Invariance in Policy Optimisation and Partial Identifiability in Reward Learning |
8, 8, 3, 3 |
Reject |
1488 |
5.5 |
Divergence-aware Federated Self-Supervised Learning |
3, 6, 8, 5 |
Accept (Poster) |
1489 |
5.5 |
NeuroSED: Learning Subgraph Similarity via Graph Neural Networks |
5, 6, 5, 6 |
Reject |
1490 |
5.4 |
Weakly Supervised Graph Clustering |
5, 5, 6, 6, 5 |
Reject |
1491 |
5.4 |
Spatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition |
6, 5, 5, 6, 5 |
Reject |
1492 |
5.4 |
Identity-Disentangled Adversarial Augmentation for Self-supervised Learning |
5, 6, 5, 6, 5 |
Reject |
1493 |
5.4 |
Proving Theorems using Incremental Learning and Hindsight Experience Replay |
3, 6, 5, 5, 8 |
Reject |
1494 |
5.4 |
PIVQGAN: Posture and Identity Disentangled Image-to-Image Translation via Vector Quantization |
6, 5, 5, 6, 5 |
Reject |
1495 |
5.4 |
Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents |
5, 3, 8, 5, 6 |
Reject |
1496 |
5.4 |
Post-Training Quantization Is All You Need to Perform Cross-Platform Learned Image Compression |
6, 6, 6, 3, 6 |
Reject |
1497 |
5.4 |
Revisit Kernel Pruning with Lottery Regulated Grouped Convolutions |
6, 5, 5, 6, 5 |
Accept (Poster) |
1498 |
5.4 |
Unraveling Model-Agnostic Meta-Learning via The Adaptation Learning Rate |
5, 5, 5, 6, 6 |
Accept (Poster) |
1499 |
5.4 |
Sparse Fuse Dense: Towards High Quality 3D Detection With Depth Completion |
5, 6, 5, 5, 6 |
Unknown |
1500 |
5.4 |
Rethinking Negative Sampling for Handling Missing Entity Annotations |
5, 6, 5, 6, 5 |
Unknown |
1501 |
5.4 |
Generalized Fourier Features for Coordinate-Based Learning of Functions on Manifolds |
10, 3, 5, 6, 3 |
Reject |
1502 |
5.4 |
Discovering Nonlinear PDEs from Scarce Data with Physics-encoded Learning |
6, 5, 6, 5, 5 |
Accept (Poster) |
1503 |
5.4 |
Adversarial Attack across Datasets |
6, 6, 5, 5, 5 |
Unknown |
1504 |
5.4 |
ACTIVE REFINEMENT OF WEAKLY SUPERVISED MODELS |
5, 5, 6, 5, 6 |
Reject |
1505 |
5.4 |
Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs |
6, 6, 6, 3, 6 |
Accept (Poster) |
1506 |
5.33 |
Adversarial twin neural networks: maximizing physics recovery for physical system |
6, 5, 5 |
Reject |
1507 |
5.33 |
Improving Discriminative Visual Representation Learning via Automatic Mixup |
5, 5, 6 |
Unknown |
1508 |
5.33 |
Learn Together, Stop Apart: a Novel Approach to Ensemble Pruning |
5, 6, 5 |
Reject |
1509 |
5.33 |
Text Generation with Efficient (Soft) $Q$-Learning |
6, 5, 5 |
Reject |
1510 |
5.33 |
SPP-RL: State Planning Policy Reinforcement Learning |
5, 3, 8 |
Reject |
1511 |
5.33 |
Training-Free Robust Multimodal Learning via Sample-Wise Jacobian Regularization |
5, 5, 6 |
Reject |
1512 |
5.33 |
Neuronal Learning Analysis using Cycle-Consistent Adversarial Networks |
6, 5, 5 |
Reject |
1513 |
5.33 |
Task-driven Discovery of Perceptual Schemas for Generalization in Reinforcement Learning |
5, 6, 5 |
Reject |
1514 |
5.33 |
Model-Based Robust Adaptive Semantic Segmentation |
6, 5, 5 |
Reject |
1515 |
5.33 |
Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis |
5, 5, 6 |
Reject |
1516 |
5.33 |
S3: Supervised Self-supervised Learning under Label Noise |
6, 5, 5 |
Reject |
1517 |
5.33 |
Locality-Based Mini Batching for Graph Neural Networks |
5, 6, 5 |
Reject |
1518 |
5.33 |
Learning to Coordinate in Multi-Agent Systems: A Coordinated Actor-Critic Algorithm and Finite-Time Guarantees |
6, 5, 5 |
Unknown |
1519 |
5.33 |
Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents |
8, 3, 5 |
Reject |
1520 |
5.33 |
Lagrangian Method for Episodic Learning |
5, 5, 6 |
Reject |
1521 |
5.33 |
Continual Learning Using Pseudo-Replay via Latent Space Sampling |
6, 5, 5 |
Unknown |
1522 |
5.33 |
ClimateGAN: Raising Climate Change Awareness by Generating Images of Floods |
6, 5, 5 |
Accept (Poster) |
1523 |
5.33 |
Spending Thinking Time Wisely: Accelerating MCTS with Virtual Expansions |
5, 3, 8 |
Reject |
1524 |
5.33 |
Unsupervised Learning of Full-Waveform Inversion: Connecting CNN and Partial Differential Equation in a Loop |
5, 3, 8 |
Accept (Poster) |
1525 |
5.33 |
Robust Generalization of Quadratic Neural Networks via Function Identification |
6, 5, 5 |
Reject |
1526 |
5.33 |
Temporal abstractions-augmented temporally contrastive learning: an alternative to the Laplacian in RL |
5, 6, 5 |
Reject |
1527 |
5.33 |
Coresets for Kernel Clustering |
3, 8, 5 |
Reject |
1528 |
5.33 |
Generative Modeling for Multitask Visual Learning |
6, 5, 5 |
Reject |
1529 |
5.33 |
Learning with convolution and pooling operations in kernel methods |
6, 5, 5 |
Reject |
1530 |
5.33 |
Kokoyi: Executable LaTeX for End-to-end Deep Learning |
5, 5, 6 |
Reject |
1531 |
5.33 |
Partial Information as Full: Reward Imputation with Sketching in Bandits |
6, 5, 5 |
Reject |
1532 |
5.33 |
A Principled Permutation Invariant Approach to Mean-Field Multi-Agent Reinforcement Learning |
3, 5, 8 |
Reject |
1533 |
5.33 |
Stability analysis of SGD through the normalized loss function |
8, 3, 5 |
Reject |
1534 |
5.33 |
STRIC: Stacked Residuals of Interpretable Components for Time Series Anomaly Detection |
5, 6, 5 |
Reject |
1535 |
5.33 |
Stochastic Projective Splitting: Solving Saddle-Point Problems with Multiple Regularizers |
5, 6, 5 |
Reject |
1536 |
5.33 |
Momentum Contrastive Autoencoder: Using Contrastive Learning for Latent Space Distribution Matching in WAE |
5, 6, 5 |
Reject |
1537 |
5.33 |
Robust and Scalable SDE Learning: A Functional Perspective |
5, 5, 6 |
Accept (Poster) |
1538 |
5.33 |
Multi-Objective Model Selection for Time Series Forecasting |
6, 5, 5 |
Reject |
1539 |
5.33 |
SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks |
6, 5, 5 |
Reject |
1540 |
5.33 |
AS-MLP: An Axial Shifted MLP Architecture for Vision |
5, 6, 5 |
Accept (Poster) |
1541 |
5.33 |
RAVE: A variational autoencoder for fast and high-quality neural audio synthesis |
8, 3, 5 |
Reject |
1542 |
5.33 |
1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed |
6, 5, 5 |
Reject |
1543 |
5.33 |
Input Convex Graph Neural Networks: An Application to Optimal Control and Design Optimization |
5, 5, 6 |
Unknown |
1544 |
5.33 |
AlignMix: Improving representations by interpolating aligned features |
5, 5, 6 |
Unknown |
1545 |
5.33 |
One-Shot Generative Domain Adaptation |
3, 8, 5 |
Reject |
1546 |
5.33 |
Uncertainty-based out-of-distribution detection requires suitable function space priors |
5, 6, 5 |
Reject |
1547 |
5.33 |
An Empirical Investigation of the Role of Pre-training in Lifelong Learning |
5, 5, 6 |
Reject |
1548 |
5.33 |
Zero-Shot Self-Supervised Learning for MRI Reconstruction |
6, 5, 5 |
Accept (Poster) |
1549 |
5.33 |
Beyond Faithfulness: A Framework to Characterize and Compare Saliency Methods |
8, 3, 5 |
Reject |
1550 |
5.33 |
Learning Identity-Preserving Transformations on Data Manifolds |
6, 5, 5 |
Reject |
1551 |
5.33 |
MQTransformer: Multi-Horizon Forecasts with Context Dependent and Feedback-Aware Attention |
5, 5, 6 |
Reject |
1552 |
5.33 |
MA-CLIP: Towards Modality-Agnostic Contrastive Language-Image Pre-training |
5, 3, 8 |
Unknown |
1553 |
5.33 |
Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamics |
5, 5, 6 |
Reject |
1554 |
5.33 |
A Study of Face Obfuscation in ImageNet |
5, 6, 5 |
Reject |
1555 |
5.33 |
Meta-free few-shot learning via representation learning with weight averaging |
5, 5, 6 |
Reject |
1556 |
5.33 |
Reynolds Equivariant and Invariant Networks |
5, 5, 6 |
Unknown |
1557 |
5.33 |
Fooling Explanations in Text Classifiers |
5, 6, 5 |
Accept (Poster) |
1558 |
5.33 |
InstaHide’s Sample Complexity When Mixing Two Private Images |
5, 5, 6 |
Reject |
1559 |
5.33 |
Dataset Condensation with Distribution Matching |
8, 3, 5 |
Unknown |
1560 |
5.33 |
CrossMatch: Improving Semi-Supervised Object Detection via Multi-Scale Consistency |
5, 5, 6 |
Unknown |
1561 |
5.33 |
Improving Out-of-Distribution Robustness via Selective Augmentation |
5, 6, 5 |
Reject |
1562 |
5.33 |
Adaptive Unbiased Teacher for Cross-Domain Object Detection |
5, 6, 5 |
Unknown |
1563 |
5.33 |
HyperTransformer: Attention-Based CNN Model Generation from Few Samples |
3, 8, 5 |
Reject |
1564 |
5.33 |
Gradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models |
3, 5, 8 |
Reject |
1565 |
5.33 |
Missingness Bias in Model Debugging |
6, 5, 5 |
Accept (Poster) |
1566 |
5.33 |
Learning to Efficiently Sample from Diffusion Probabilistic Models |
5, 5, 6 |
Reject |
1567 |
5.33 |
Long Document Summarization with Top-Down and Bottom-Up Representation Inference |
6, 5, 5 |
Reject |
1568 |
5.33 |
Protecting Your NLG Models with Semantic and Robust Watermarks |
5, 5, 6 |
Unknown |
1569 |
5.33 |
A Simple Approach to Adversarial Robustness in Few-shot Image Classification |
6, 5, 5 |
Reject |
1570 |
5.33 |
$p$-Laplacian Based Graph Neural Networks |
8, 3, 5 |
Reject |
1571 |
5.33 |
A Generalised Inverse Reinforcement Learning Framework |
5, 5, 6 |
Reject |
1572 |
5.33 |
Back to Basics: Efficient Network Compression via IMP |
5, 6, 5 |
Reject |
1573 |
5.33 |
A Simple Reward-free Approach to Constrained Reinforcement Learning |
6, 5, 5 |
Reject |
1574 |
5.25 |
Learning to perceive objects by prediction |
3, 5, 5, 8 |
Reject |
1575 |
5.25 |
Connecting Graph Convolution and Graph PCA |
5, 6, 5, 5 |
Reject |
1576 |
5.25 |
Language Modulated Detection and Detection Modulated Language Grounding in 2D and 3D Scenes |
5, 6, 5, 5 |
Unknown |
1577 |
5.25 |
Subpixel object segmentation using wavelets and multiresolution analysis |
6, 6, 3, 6 |
Reject |
1578 |
5.25 |
Multilevel physics informed neural networks (MPINNs) |
3, 5, 8, 5 |
Reject |
1579 |
5.25 |
Learning to Abstain in the Presence of Uninformative Data |
3, 6, 6, 6 |
Reject |
1580 |
5.25 |
Scale-Invariant Teaching for Semi-Supervised Object Detection |
5, 5, 5, 6 |
Unknown |
1581 |
5.25 |
Tight lower bounds for Differentially Private ERM |
5, 3, 5, 8 |
Reject |
1582 |
5.25 |
Representing Mixtures of Word Embeddings with Mixtures of Topic Embeddings |
5, 5, 6, 5 |
Accept (Poster) |
1583 |
5.25 |
Causal Reinforcement Learning using Observational and Interventional Data |
5, 5, 5, 6 |
Reject |
1584 |
5.25 |
Visual hyperacuity with moving sensor and recurrent neural computations |
3, 10, 5, 3 |
Accept (Poster) |
1585 |
5.25 |
Cross-Trajectory Representation Learning for Zero-Shot Generalization in RL |
6, 3, 6, 6 |
Accept (Poster) |
1586 |
5.25 |
Breaking Down Questions for Outside-Knowledge VQA |
5, 5, 6, 5 |
Unknown |
1587 |
5.25 |
Task Conditioned Stochastic Subsampling |
3, 5, 5, 8 |
Reject |
1588 |
5.25 |
Factored World Models for Zero-Shot Generalization in Robotic Manipulation |
6, 5, 5, 5 |
Reject |
1589 |
5.25 |
Motion Planning Transformers: One Model to Plan them All |
3, 6, 6, 6 |
Reject |
1590 |
5.25 |
The Low-Rank Simplicity Bias in Deep Networks |
5, 5, 6, 5 |
Reject |
1591 |
5.25 |
Multi-Subspace Structured Meta-Learning |
6, 5, 5, 5 |
Unknown |
1592 |
5.25 |
Unconditional Diffusion Guidance |
6, 5, 5, 5 |
Reject |
1593 |
5.25 |
Sample Complexity of Offline Reinforcement Learning with Deep ReLU Networks |
5, 6, 5, 5 |
Unknown |
1594 |
5.25 |
GIR Framework: Learning Graph Positional Embeddings with Anchor Indication and Path Encoding |
5, 6, 5, 5 |
Reject |
1595 |
5.25 |
Tropical Geometrical Zonotope Reduction as Applied to Neural Network Compression. |
5, 5, 5, 6 |
Accept (Poster) |
1596 |
5.25 |
A Unified Knowledge Distillation Framework for Deep Directed Graphical Models |
5, 5, 5, 6 |
Reject |
1597 |
5.25 |
Learning Equivariances and Partial Equivariances From Data |
6, 5, 5, 5 |
Reject |
1598 |
5.25 |
Code Editing from Few Exemplars by Adaptive Multi-Extent Composition |
5, 5, 6, 5 |
Reject |
1599 |
5.25 |
Intriguing Properties of Input-dependent Randomized Smoothing |
5, 5, 3, 8 |
Reject |
1600 |
5.25 |
Graph Attention Multi-layer Perceptron |
6, 3, 6, 6 |
Reject |
1601 |
5.25 |
A Good Representation Detects Noisy Labels |
5, 6, 5, 5 |
Reject |
1602 |
5.25 |
How much pre-training is enough to discover a good subnetwork? |
6, 5, 5, 5 |
Unknown |
1603 |
5.25 |
Improving Meta-Continual Learning Representations with Representation Replay |
5, 6, 5, 5 |
Reject |
1604 |
5.25 |
Concentric Spherical GNN for 3D Representation Learning |
6, 5, 5, 5 |
Reject |
1605 |
5.25 |
A new look at fairness in stochastic multi-armed bandit problems |
5, 5, 5, 6 |
Reject |
1606 |
5.25 |
Zero-shot Cross-lingual Conversational Semantic Role Labeling |
5, 6, 5, 5 |
Unknown |
1607 |
5.25 |
GRAPHIX: A Pre-trained Graph Edit Model for Automated Program Repair |
5, 5, 6, 5 |
Reject |
1608 |
5.25 |
Towards Understanding Label Smoothing |
5, 5, 5, 6 |
Reject |
1609 |
5.25 |
FitVid: High-Capacity Pixel-Level Video Prediction |
5, 5, 5, 6 |
Reject |
1610 |
5.25 |
Gradient Assisted Learning |
5, 5, 5, 6 |
Unknown |
1611 |
5.25 |
Guided-TTS:Text-to-Speech with Untranscribed Speech |
8, 5, 5, 3 |
Reject |
1612 |
5.25 |
Non-reversible Parallel Tempering for Uncertainty Approximation in Deep Learning |
8, 5, 3, 5 |
Reject |
1613 |
5.25 |
Faster Reinforcement Learning with Value Target Lower Bounding |
6, 6, 3, 6 |
Reject |
1614 |
5.25 |
Adversarial Collaborative Learning on Non-IID Features |
5, 8, 3, 5 |
Reject |
1615 |
5.25 |
Online Unsupervised Learning of Visual Representations and Categories |
3, 6, 6, 6 |
Reject |
1616 |
5.25 |
TaCE: Time-aware Convolutional Embedding Learning for Temporal Knowledge Graph Completion |
6, 6, 6, 3 |
Unknown |
1617 |
5.25 |
Monotonicity as a requirement and as a regularizer: efficient methods and applications |
6, 5, 5, 5 |
Reject |
1618 |
5.25 |
Non-Denoising Forward-Time Diffusions |
8, 3, 5, 5 |
Reject |
1619 |
5.25 |
Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space |
5, 5, 5, 6 |
Reject |
1620 |
5.25 |
Transductive Universal Transport for Zero-Shot Action Recognition |
6, 5, 5, 5 |
Reject |
1621 |
5.25 |
On the regularization landscape for the linear recommendation models |
5, 5, 5, 6 |
Reject |
1622 |
5.25 |
Disentangling Properties of Contrastive Methods |
5, 5, 8, 3 |
Reject |
1623 |
5.25 |
Memory Replay with Data Compression for Continual Learning |
6, 6, 3, 6 |
Accept (Poster) |
1624 |
5.25 |
On Pseudo-Labeling for Class-Mismatch Semi-Supervised Learning |
6, 6, 3, 6 |
Reject |
1625 |
5.25 |
PACE: A Parallelizable Computation Encoder for Directed Acyclic Graphs |
5, 5, 6, 5 |
Reject |
1626 |
5.25 |
ZeroSARAH: Efficient Nonconvex Finite-Sum Optimization with Zero Full Gradient Computations |
3, 5, 5, 8 |
Reject |
1627 |
5.25 |
Consistent Counterfactuals for Deep Models |
6, 6, 3, 6 |
Accept (Poster) |
1628 |
5.25 |
Unsupervised Learning of Neurosymbolic Encoders |
5, 6, 5, 5 |
Reject |
1629 |
5.25 |
LiST: Lite Self-training Makes Efficient Few-shot Learners |
5, 8, 5, 3 |
Unknown |
1630 |
5.25 |
Improving Long-Horizon Imitation Through Language Prediction |
5, 6, 5, 5 |
Reject |
1631 |
5.25 |
How Does the Task Landscape Affect MAML Performance? |
5, 5, 6, 5 |
Reject |
1632 |
5.25 |
Robust Models Are More Interpretable Because Attributions Look Normal |
3, 6, 6, 6 |
Reject |
1633 |
5.25 |
Beyond Examples: Constructing Explanation Space for Explaining Prototypes |
5, 8, 5, 3 |
Reject |
1634 |
5.25 |
HyperCGAN: Text-to-Image Synthesis with HyperNet-Modulated Conditional Generative Adversarial Networks |
5, 6, 5, 5 |
Reject |
1635 |
5.25 |
FSL: Federated Supermask Learning |
6, 3, 6, 6 |
Reject |
1636 |
5.25 |
Adaptive Generalization for Semantic Segmentation |
5, 6, 5, 5 |
Reject |
1637 |
5.25 |
Automatic Concept Extraction for Concept Bottleneck-based Video Classification |
6, 5, 5, 5 |
Reject |
1638 |
5.25 |
On the Convergence of Nonconvex Continual Learning with Adaptive Learning Rate |
5, 3, 5, 8 |
Reject |
1639 |
5.25 |
Switch Spaces: Learning Product Spaces with Sparse Gating |
5, 6, 5, 5 |
Unknown |
1640 |
5.25 |
Optimizing Class Distribution in Memory for Multi-Label Continual Learning |
5, 6, 5, 5 |
Unknown |
1641 |
5.25 |
Continuous Control with Action Quantization from Demonstrations |
5, 5, 6, 5 |
Reject |
1642 |
5.25 |
Compressed-VFL: Communication-Efficient Learning with Vertically Partitioned Data |
5, 5, 5, 6 |
Reject |
1643 |
5.25 |
Stepping Back to SMILES Transformers for Fast Molecular Representation Inference |
5, 3, 8, 5 |
Reject |
1644 |
5.25 |
Memory-Constrained Policy Optimization |
5, 8, 5, 3 |
Reject |
1645 |
5.25 |
Efficient Wasserstein and Sinkhorn Policy Optimization |
6, 6, 3, 6 |
Reject |
1646 |
5.25 |
VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning |
6, 6, 6, 3 |
Accept (Poster) |
1647 |
5.25 |
Iterative Memory Network for Long Sequential User Behavior Modeling in Recommender Systems |
5, 5, 5, 6 |
Reject |
1648 |
5.25 |
Finding lost DG: Explaining domain generalization via model complexity |
8, 5, 5, 3 |
Reject |
1649 |
5.25 |
Offline Reinforcement Learning with Resource Constrained Online Deployment |
5, 6, 5, 5 |
Reject |
1650 |
5.25 |
Deep Active Learning by Leveraging Training Dynamics |
6, 6, 3, 6 |
Reject |
1651 |
5.25 |
EF21 with Bells & Whistles: Practical Algorithmic Extensions of Modern Error Feedback |
5, 5, 5, 6 |
Reject |
1652 |
5.25 |
Demystifying How Self-Supervised Features Improve Training from Noisy Labels |
6, 5, 5, 5 |
Reject |
1653 |
5.25 |
Fair Representation Learning through Implicit Path Alignment |
3, 6, 6, 6 |
Unknown |
1654 |
5.25 |
Wavelet Feature Maps Compression for Low Bandwidth Convolutional Neural Networks |
5, 6, 5, 5 |
Reject |
1655 |
5.25 |
Modular Action Concept Grounding in Semantic Video Prediction |
5, 5, 5, 6 |
Unknown |
1656 |
5.25 |
Free Hyperbolic Neural Networks with Limited Radii |
5, 5, 3, 8 |
Unknown |
1657 |
5.25 |
Rethinking Again the Value of Network Pruning -- A Dynamical Isometry Perspective |
8, 3, 5, 5 |
Reject |
1658 |
5.25 |
Universal Controllers with Differentiable Physics for Online System Identification |
5, 6, 5, 5 |
Reject |
1659 |
5.25 |
Defending Graph Neural Networks via Tensor-Based Robust Graph Aggregation |
6, 6, 6, 3 |
Reject |
1660 |
5.25 |
Information-Theoretic Generalization Bounds for Iterative Semi-Supervised Learning |
5, 5, 5, 6 |
Reject |
1661 |
5.25 |
Generalizable Learning to Optimize into Wide Valleys |
5, 6, 5, 5 |
Reject |
1662 |
5.25 |
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile |
6, 5, 5, 5 |
Unknown |
1663 |
5.25 |
Successive POI Recommendation via Brain-inspired Spatiotemporal Aware Representation |
5, 5, 5, 6 |
Reject |
1664 |
5.25 |
Structured Energy Network as a dynamic loss function. Case study. A case study with multi-label Classification |
6, 6, 6, 3 |
Reject |
1665 |
5.25 |
Disentangled Mask Attention in Transformer |
6, 5, 5, 5 |
Unknown |
1666 |
5.25 |
Tell me why!—Explanations support learning relational and causal structure |
6, 3, 6, 6 |
Reject |
1667 |
5.25 |
SGDEM: stochastic gradient descent with energy and momentum |
5, 5, 5, 6 |
Reject |
1668 |
5.25 |
Avoiding Robust Misclassifications for Improved Robustness without Accuracy Loss |
3, 5, 5, 8 |
Reject |
1669 |
5.25 |
Structured Stochastic Gradient MCMC |
5, 3, 8, 5 |
Reject |
1670 |
5.25 |
Randomized Primal-Dual Coordinate Method for Large-scale Linearly Constrained Nonsmooth Nonconvex Optimization |
6, 3, 6, 6 |
Reject |
1671 |
5.25 |
A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning |
5, 8, 5, 3 |
Reject |
1672 |
5.25 |
Feature Selection in the Contrastive Analysis Setting |
3, 8, 5, 5 |
Reject |
1673 |
5.25 |
SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient |
6, 3, 6, 6 |
Reject |
1674 |
5.25 |
Mismatched No More: Joint Model-Policy Optimization for Model-Based RL |
6, 3, 6, 6 |
Reject |
1675 |
5.25 |
Visual Representation Learning over Latent Domains |
6, 6, 6, 3 |
Accept (Poster) |
1676 |
5.25 |
Distributionally Robust Learning for Uncertainty Calibration under Domain Shift |
6, 5, 5, 5 |
Reject |
1677 |
5.25 |
Geometric Algebra Attention Networks for Small Point Clouds |
6, 6, 6, 3 |
Reject |
1678 |
5.25 |
DAdaQuant: Doubly-adaptive quantization for communication-efficient Federated Learning |
5, 5, 8, 3 |
Reject |
1679 |
5.25 |
Fast Finite Width Neural Tangent Kernel |
6, 6, 3, 6 |
Reject |
1680 |
5.25 |
Maximizing Ensemble Diversity in Deep Reinforcement Learning |
3, 6, 6, 6 |
Accept (Poster) |
1681 |
5.25 |
Learning to Collaborate |
5, 3, 5, 8 |
Reject |
1682 |
5.25 |
Attention-based Feature Aggregation |
5, 5, 5, 6 |
Unknown |
1683 |
5.25 |
Asynchronous Multi-Agent Actor-Critic with Macro-Actions |
5, 6, 5, 5 |
Reject |
1684 |
5.25 |
Learning Controllable Elements Oriented Representations for Reinforcement Learning |
6, 5, 5, 5 |
Reject |
1685 |
5.25 |
General Incremental Learning with Domain-aware Categorical Representations |
5, 6, 5, 5 |
Unknown |
1686 |
5.25 |
Few-shot graph link prediction with domain adaptation |
5, 8, 5, 3 |
Reject |
1687 |
5.25 |
MOG: Molecular Out-of-distribution Generation with Energy-based Models |
5, 5, 6, 5 |
Unknown |
1688 |
5.25 |
Towards General Function Approximation in Zero-Sum Markov Games |
6, 6, 3, 6 |
Accept (Poster) |
1689 |
5.25 |
FedNAS: Federated Deep Learning via Neural Architecture Search |
5, 5, 5, 6 |
Reject |
1690 |
5.25 |
Boundary Graph Neural Networks for 3D Simulations |
5, 5, 5, 6 |
Reject |
1691 |
5.25 |
Composing Partial Differential Equations with Physics-Aware Neural Networks |
6, 6, 3, 6 |
Reject |
1692 |
5.25 |
Sequential Reptile: Inter-Task Gradient Alignment for Multilingual Learning |
6, 5, 5, 5 |
Accept (Poster) |
1693 |
5.25 |
Teamwork makes von Neumann work:Min-Max Optimization in Two-Team Zero-Sum Games |
6, 6, 6, 3 |
Reject |
1694 |
5.25 |
Exploring Complicated Search Spaces with Interleaving-Free Sampling |
3, 5, 8, 5 |
Unknown |
1695 |
5.25 |
Communicate Then Adapt: An Effective Decentralized Adaptive Method for Deep Training |
5, 8, 5, 3 |
Reject |
1696 |
5.25 |
Regularizing Deep Neural Networks with Stochastic Estimators of Hessian Trace |
5, 3, 8, 5 |
Reject |
1697 |
5.25 |
Pseudo Knowledge Distillation: Towards Learning Optimal Instance-specific Label Smoothing Regularization |
5, 5, 6, 5 |
Reject |
1698 |
5.25 |
Propagating Distributions through Neural Networks |
3, 6, 6, 6 |
Reject |
1699 |
5.25 |
A fast and accurate splitting method for optimal transport: analysis and implementation |
3, 6, 6, 6 |
Accept (Poster) |
1700 |
5.25 |
Learning from One and Only One Shot |
5, 5, 5, 6 |
Reject |
1701 |
5.25 |
Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation |
5, 5, 5, 6 |
Reject |
1702 |
5.25 |
Randomized Signature Layers for Signal Extraction in Time Series Data |
6, 5, 5, 5 |
Reject |
1703 |
5.25 |
Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness |
5, 6, 5, 5 |
Reject |
1704 |
5.25 |
Hybrid Cloud-Edge Networks for Efficient Inference |
6, 5, 5, 5 |
Reject |
1705 |
5.25 |
Generating Symbolic Reasoning Problems with Transformer GANs |
5, 5, 3, 8 |
Reject |
1706 |
5.25 |
Differentiable Discrete Device-to-System Codesign for Optical Neural Networks via Gumbel-Softmax |
5, 5, 6, 5 |
Unknown |
1707 |
5.25 |
Bypassing Logits Bias in Online Class-Incremental Learning with a Generative Framework |
5, 5, 5, 6 |
Reject |
1708 |
5.25 |
Parallel Deep Neural Networks Have Zero Duality Gap |
5, 5, 6, 5 |
Reject |
1709 |
5.25 |
Cross Project Software Vulnerability Detection via Domain Adaptation and Max-Margin Principle |
8, 5, 5, 3 |
Unknown |
1710 |
5.25 |
AutoNF: Automated Architecture Optimization of Normalizing Flows Using a Mixture Distribution Formulation |
8, 5, 5, 3 |
Reject |
1711 |
5.25 |
Semi-Empirical Objective Functions for Neural MCMC Proposal Optimization |
5, 8, 5, 3 |
Reject |
1712 |
5.25 |
Model Agnostic Interpretability for Multiple Instance Learning |
6, 5, 5, 5 |
Accept (Poster) |
1713 |
5.25 |
Adaptive Q-learning for Interaction-Limited Reinforcement Learning |
3, 6, 6, 6 |
Reject |
1714 |
5.25 |
On the Practicality of Deterministic Epistemic Uncertainty |
3, 8, 5, 5 |
Reject |
1715 |
5.25 |
Practical Integration via Separable Bijective Networks |
8, 6, 1, 6 |
Accept (Poster) |
1716 |
5.25 |
ViViT: Curvature access through the generalized Gauss-Newton's low-rank structure |
5, 6, 5, 5 |
Reject |
1717 |
5.25 |
Revisiting the Lottery Ticket Hypothesis: A Ramanujan Graph Perspective |
6, 5, 5, 5 |
Reject |
1718 |
5.25 |
Transfer and Marginalize: Explaining Away Label Noise with Privileged Information |
6, 6, 3, 6 |
Reject |
1719 |
5.25 |
LEARNING PHONEME-LEVEL DISCRETE SPEECH REPRESENTATION WITH WORD-LEVEL SUPERVISION |
6, 5, 5, 5 |
Unknown |
1720 |
5.25 |
Task-Agnostic Graph Neural Explanations |
5, 5, 5, 6 |
Reject |
1721 |
5.25 |
Towards Coherent and Consistent Use of Entities in Narrative Generation |
5, 5, 5, 6 |
Reject |
1722 |
5.25 |
Understanding AdamW through Proximal Methods and Scale-Freeness |
6, 3, 6, 6 |
Reject |
1723 |
5.25 |
Intrusion-Free Graph Mixup |
8, 3, 5, 5 |
Reject |
1724 |
5.25 |
Benign Overfitting in Adversarially Robust Linear Classification |
5, 5, 6, 5 |
Reject |
1725 |
5.25 |
Learning Graph Structure from Convolutional Mixtures |
5, 5, 5, 6 |
Reject |
1726 |
5.25 |
CoSe-Co: Text Conditioned Generative CommonSense Contextualizer |
5, 5, 6, 5 |
Unknown |
1727 |
5.25 |
Detecting Modularity in Deep Neural Networks |
5, 5, 5, 6 |
Reject |
1728 |
5.25 |
Conditional set generation using Seq2seq models |
5, 6, 5, 5 |
Reject |
1729 |
5.25 |
Self-Slimming Vision Transformer |
5, 6, 5, 5 |
Unknown |
1730 |
5.25 |
AI-SARAH: Adaptive and Implicit Stochastic Recursive Gradient Methods |
5, 5, 5, 6 |
Reject |
1731 |
5.25 |
AutoOED: Automated Optimal Experimental Design Platform with Data- and Time-Efficient Multi-Objective Optimization |
5, 5, 5, 6 |
Reject |
1732 |
5.25 |
DAIR: Data Augmented Invariant Regularization |
5, 6, 5, 5 |
Unknown |
1733 |
5.25 |
Certified Patch Robustness via Smoothed Vision Transformers |
5, 5, 5, 6 |
Unknown |
1734 |
5.25 |
Training Meta-Surrogate Model for Transferable Adversarial Attack |
5, 6, 5, 5 |
Unknown |
1735 |
5.2 |
TorchGeo: deep learning with geospatial data |
5, 5, 5, 6, 5 |
Reject |
1736 |
5.2 |
Learning to Learn across Diverse Data Biases in Deep Face Recognition |
5, 8, 5, 5, 3 |
Unknown |
1737 |
5.2 |
ZerO Initialization: Initializing Residual Networks with only Zeros and Ones |
5, 5, 5, 6, 5 |
Reject |
1738 |
5.2 |
Depth Without the Magic: Inductive Bias of Natural Gradient Descent |
5, 5, 6, 5, 5 |
Reject |
1739 |
5.2 |
The Needle in the haystack: Out-distribution aware Self-training in an Open-World Setting |
5, 8, 5, 3, 5 |
Reject |
1740 |
5.2 |
Expected Improvement-based Contextual Bandits |
5, 3, 6, 6, 6 |
Reject |
1741 |
5.2 |
Digging Into Output Representation for Monocular 3D Object Detection |
8, 5, 5, 5, 3 |
Unknown |
1742 |
5.2 |
Local Calibration: Metrics and Recalibration |
5, 5, 5, 5, 6 |
Reject |
1743 |
5.2 |
Dense-to-Sparse Gate for Mixture-of-Experts |
5, 5, 6, 5, 5 |
Reject |
1744 |
5.2 |
Discovering the neural correlate informed nosological relation among multiple neuropsychiatric disorders through dual utilisation of diagnostic information |
6, 6, 5, 1, 8 |
Reject |
1745 |
5.2 |
Reinforcement Learning for Adaptive Mesh Refinement |
6, 5, 5, 5, 5 |
Reject |
1746 |
5.2 |
Reasoning With Hierarchical Symbols: Reclaiming Symbolic Policies For Visual Reinforcement Learning |
3, 6, 8, 3, 6 |
Reject |
1747 |
5.2 |
Speech-MLP: a simple MLP architecture for speech processing |
5, 8, 5, 3, 5 |
Reject |
1748 |
5.2 |
Gradient Explosion and Representation Shrinkage in Infinite Networks |
5, 5, 8, 3, 5 |
Reject |
1749 |
5.2 |
Fundamental Limits of Transfer Learning in Binary Classifications |
5, 6, 3, 6, 6 |
Reject |
1750 |
5.2 |
Private Multi-Winner Voting For Machine Learning |
5, 8, 5, 5, 3 |
Reject |
1751 |
5.2 |
Multi-Agent Language Learning: Symbolic Mapping |
3, 5, 6, 6, 6 |
Reject |
1752 |
5.2 |
Improving Robustness with Optimal Transport based Adversarial Generalization |
5, 5, 6, 5, 5 |
Unknown |
1753 |
5 |
Structured Uncertainty in the Observation Space of Variational Autoencoders |
6, 5, 3, 6 |
Reject |
1754 |
5 |
Wakening Past Concepts without Past Data: Class-incremental Learning from Placebos |
6, 6, 3, 5 |
Reject |
1755 |
5 |
What can multi-cloud configuration learn from AutoML? |
5, 5, 5, 5 |
Reject |
1756 |
5 |
Automated Mobile Attention KPConv Networks via A Wide & Deep Predictor |
6, 6, 3, 5 |
Reject |
1757 |
5 |
MutexMatch: Semi-supervised Learning with Mutex-based Consistency Regularization |
5, 5, 5 |
Unknown |
1758 |
5 |
Model-Agnostic Meta-Attack: Towards Reliable Evaluation of Adversarial Robustness |
3, 6, 6 |
Reject |
1759 |
5 |
Einops: Clear and Reliable Tensor Manipulations with Einstein-like Notation |
8, 3, 6, 3 |
Accept (Oral) |
1760 |
5 |
Enforcing physics-based algebraic constraints for inference of PDE models on unstructured grids |
5, 5, 5, 5 |
Reject |
1761 |
5 |
Overcoming Label Ambiguity with Multi-label Iterated Learning |
5, 5, 5, 5 |
Unknown |
1762 |
5 |
CheXT: Knowledge-Guided Cross-Attention Transformer for Abnormality Classification and Localization in Chest X-rays |
5, 5, 5 |
Reject |
1763 |
5 |
Short-term memory in neural language models |
3, 5, 6, 6, 5 |
Reject |
1764 |
5 |
Communicating Natural Programs to Humans and Machines |
5, 5, 5 |
Reject |
1765 |
5 |
On The Quality Assurance Of Concept-Based Representations |
5, 5, 5 |
Reject |
1766 |
5 |
Effective Polynomial Filter Adaptation for Graph Neural Networks |
5, 5, 5, 5 |
Reject |
1767 |
5 |
Cross Domain Ensemble Distillation for Domain Generalization |
3, 6, 6 |
Unknown |
1768 |
5 |
Data-centric Semi-supervised Learning |
6, 5, 6, 3 |
Unknown |
1769 |
5 |
Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots |
6, 5, 3, 6 |
Reject |
1770 |
5 |
Fieldwise Factorized Networks for Tabular Data Classification |
6, 3, 5, 6 |
Reject |
1771 |
5 |
Value-aware transformers for 1.5d data |
6, 3, 6 |
Reject |
1772 |
5 |
Object-Centric Neural Scene Rendering |
5, 5, 5, 5 |
Reject |
1773 |
5 |
Improving Generative Adversarial Networks via Adversarial Learning in Latent Space |
5, 3, 6, 6 |
Reject |
1774 |
5 |
Self-Distribution Distillation: Efficient Uncertainty Estimation |
5, 5, 5, 5 |
Reject |
1775 |
5 |
Closed-Loop Control of Additive Manufacturing via Reinforcement Learning |
5, 5, 5 |
Reject |
1776 |
5 |
Resolving label uncertainty with implicit generative models |
3, 5, 6, 6 |
Reject |
1777 |
5 |
COLA: Consistent Learning with Opponent-Learning Awareness |
3, 8, 6, 3 |
Reject |
1778 |
5 |
Imperceptible Black-box Attack via Refining in Salient Region |
5, 5, 5, 5 |
Reject |
1779 |
5 |
Diverse Imitation Learning via Self-OrganizingGenerative Models |
6, 6, 3 |
Unknown |
1780 |
5 |
Reference-Limited Compositional Learning: A Realistic Assessment for Human-level Compositional Generalization |
5, 5, 5, 5 |
Unknown |
1781 |
5 |
Self-Distilled Pruning Of Neural Networks |
6, 3, 5, 5, 6 |
Unknown |
1782 |
5 |
RNAS: Robust Network Architecture Search beyond DARTS |
5, 5, 5 |
Unknown |
1783 |
5 |
MLP-based architecture with variable length input for automatic speech recognition |
6, 3, 5, 6 |
Reject |
1784 |
5 |
State-Action Joint Regularized Implicit Policy for Offline Reinforcement Learning |
6, 3, 6 |
Reject |
1785 |
5 |
Interrogating Paradigms in Self-supervised Graph Representation Learning |
5, 5, 5, 5 |
Reject |
1786 |
5 |
Neural Tangent Kernel Empowered Federated Learning |
5, 5, 5, 5 |
Reject |
1787 |
5 |
Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution |
6, 5, 3, 6 |
Reject |
1788 |
5 |
Introspective Learning : A Two-Stage approach for Inference in Neural Networks |
6, 6, 5, 3 |
Reject |
1789 |
5 |
I-PGD-AT: Efficient Adversarial Training via Imitating Iterative PGD Attack |
3, 5, 6, 6 |
Reject |
1790 |
5 |
Learning Continuous Environment Fields via Implicit Functions |
6, 8, 1 |
Accept (Poster) |
1791 |
5 |
Teacher's pet: understanding and mitigating biases in distillation |
3, 6, 5, 6 |
Reject |
1792 |
5 |
Decentralized Cross-Entropy Method for Model-Based Reinforcement Learning |
6, 6, 3 |
Reject |
1793 |
5 |
Adversarial Weight Perturbation Improves Generalization in Graph Neural Networks |
6, 6, 5, 3 |
Reject |
1794 |
5 |
Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling |
5, 6, 3, 6 |
Unknown |
1795 |
5 |
Understanding and Scheduling Weight Decay |
3, 8, 6, 3 |
Reject |
1796 |
5 |
Antonymy-Synonymy Discrimination through the Repelling Parasiamese Neural Network |
6, 3, 6 |
Reject |
1797 |
5 |
A framework of deep neural networks via the solution operator of partial differential equations |
6, 3, 5, 6 |
Reject |
1798 |
5 |
Constrained Discrete Black-Box Optimization using Mixed-Integer Programming |
5, 6, 3, 6 |
Reject |
1799 |
5 |
INFERNO: Inferring Object-Centric 3D Scene Representations without Supervision |
5, 5, 5, 5 |
Reject |
1800 |
5 |
Trident Pyramid Networks: The importance of processing at the feature pyramid level for better object detection |
6, 3, 6, 5 |
Reject |
1801 |
5 |
Continuous Control With Ensemble Deep Deterministic Policy Gradients |
|
|