This page is an archive of the Deep Learning Paper Reading Meeting. you would like to attend the meeting or have any questions, Write in the GitHub issue table or email us at 'tfkeras@kakao.com'
Tasks | Paper | Link | Performance Index |
---|---|---|---|
NLP | Attention is all you need | Youtube Paper |
Abstractive Text Summarization, Constituency Parsing |
NLP | BERT | Youtube paper |
Autoencoding Transformers, Transformers, Language Models |
NLP | ERNIE | Youtube paper |
Chinese Named Entity Recognition, Chinese Sentence Pair Classification |
NLP | RoBERTa | Youtube paper |
Autoencoding Transformers, Transformers |
NLP | XLNET | Youtube paper |
Autoregressive Transformers, Transformers |
NLP | SentenceBert | Youtube | Linear-Probe Classification, Semantic Similarity |
NLP | Defending Against neural fake news | Youtube | Fake News Detection, Text Generation |
NLP | Transformer-XL | Youtube blog |
Language Modelling |
NLP | Understanding back translation at scale | Youtube blog |
Machine Translation, Translation |
NLP | Deep Contextualized Word Representations | Youtube | Citation Intent Classification , Conversational Response Selection |
NLP | Univiersal LM Fine-tuning for text classification | Youtube | Classification, General Classification |
NLP | Subword-level Word Vector Representations for Korean | Youtube | Document Classification, Language Modelling |
NLP | A Decomposable Attention Model for Natural Language Inference | Youtube | Natural Language Inference |
NLP | Reformer | Youtube | Transformers |
NLP | Neural Machine Translation by Jointly Learning to Align and Translate | Youtube | Dialogue Generation, Machine Translation |
NLP | ELECTRA | Youtube | Autoencoding Transformers |
, Transformers | |||
NLP | SBERT-WK | Youtube | Semantic Textual Similarity, Sentence Embedding |
NLP | Revealing the Dark Secrets of BERT | Youtube | BERT |
NLP | PEGASUS | Youtube | Abstractive Text Summarization |
NLP | Document-level Neural Machine Translation with Inter-Sentence Attention | Youtube | Machine Translation, Translation |
NLP | Phrase-Based & Neural Unsupervised Machine | Youtube | Translation, Unsupervised Machine Translation |
NLP | BART | Youtube | Sequence To Sequence Models, Transformers |
NLP | BAE | Youtube | Adversarial Attack, Adversarial Text |
NLP | A Generative Model for Joint Natural Language Understanding and Generation | Youtube | Natural Language Understanding, Task-Oriented Dialogue Systems |
NLP | Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training | Youtube | Language Modelling, self-Supervised Learning |
NLP | Graph Attention Networks | Youtube | Document Classification, Graph Attention |
NLP | Switch Transformers | Youtube | Language Modelling, Question Answering |
NLP | DeText: A Deep Text Ranking Framework with BERT | Youtube | Ranking |
NLP | Face book Chat bot , Blender bot | Youtube | Chatbot |
NLP | Extracting Training Data from Large Language Models | Youtube | Language Modelling |
NLP | Longformer: The Long-Document Transformer | Youtube | Language Modelling, Question Answering |
NLP | Visualizing and Measuring the Geometry of BERT | Youtube | Word Embeddings |
NLP | Encode, Tag, Realize High Precision Text Editing | Youtube | Abstractive Text Summarization, Sentence Fusion |
NLP | multimodal transformer for unaligned multimodal language sequences | Youtube | Multimodal Sentiment Analysis, Time Series |
NLP | SCGPT : Few-shot Natural Language Generation for Task-Oriented Dialog | Youtube | Data-to-Text Generation, Few-Shot Learning |
NLP | ColBERT: Efficient and Effective Passage Search viaContextualized Late Interaction over BERT | Youtube | Document Ranking, Information Retrieval |
NLP | Restoring and Mining the Records of the Joseon Dynasty via Neural LanguageModeling and Machine Translation | Youtube | Language Modelling, Machine Translation |
NLP | Improving Factual Completeness and Consistency of Image to Text Radiology Report Generation | Youtube | Natural Language Inference, Text Generation |
NLP | FinBERT | Youtube | Language Modelling, Pretrained Language Models |
NLP | LayoutLM: Pre-training of Text and Layout for Document Image Understanding | Youtube | Document Image Classification, Document Layout Analysis |
NLP | Query Suggestions as Summarization in Exploratory Search | Youtube | Query suggestions |
NLP | H-Transformer-1D Paper: Fast One Dimensional Hierarchical Attention For Sequences | Youtube | Language Modelling |
NLP | End-to-End Progressive Multi-Task Learning Framework for Medical Named Entity Recognition and Normalization | Youtube | Knowledge Graphs, Medical Named Entity Recognition |
NLP | DISEASES : Text mining and data integration of disease–gene associations | Youtube | Text mining, Data integration, Information extraction |
NLP | RoFormer: Enhanced Transformer with Rotary Position Embedding | Youtube | Semantic Text Matching |
NLP | A Multiscale Visualization of Attention in the Transformer Model | Youtube | Transformer |
NLP | CAST: Enhancing Code Summarization with Hierarchical Splitting and Reconstruction of Abstract Syntax Trees | Youtube | Software Engineering |
NLP | MERL: Multimodal Event Representation Learning in Heterogeneous Embedding Spaces | Youtube | Language Grounding, Multi-modal NLP |
NLP | Big Bird - Transformers for Longer Sequences | Youtube | Linguistic Acceptability, Natural Language Inference |
NLP | Decoding-Enhanced BERT with Disentangled Attention | Youtube | Common Sense Reasoning, Coreference Resolution |
NLP | SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis | Youtube | Aspect-Based Sentiment Analysis, Language Modelling |
NLP | IMPROVING BERT FINE-TUNING VIA SELF-ENSEMBLE AND SELF-DISTILLATION | Youtube | Natural Language Inference, Text Classification |
NLP | ACHIEVING HUMAN PARITY ON VISUAL QUESTION ANSWERING | Youtube | question-answering,Question Answering |
NLP | Deep Encoder, Shallow Decoder: Reevaluating non- autoregressive machine translation | Youtube | Knowledge Distillation, Machine Translation |
NLP | LaMDA : Language Models for Dialog Applications | Youtube | Information Retrieval |
NLP | Competition-Level Code Generation with AlphaCode | Youtube | |
NLP | Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks | Youtube | |
NLP | SimCLS: A Simple Framework for Contrastive Learning of Abstractive Summarization | Youtube | |
NLP | Graph-Bert: Only Attention is Needed for Learning Graph Representations | Youtube | |
NLP | SimCSE:Simple Contrastive Learning of Sentence Embedding | Youtube | |
NLP | Typical decoding for Natural Language | Youtube | |
NLP | Perceiver IO : A GENERAL ARCHITECTURE FOR STRUCTURED INPUTS & OUTPUTS | Youtube | |
NLP | Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference | Youtube | |
NLP | Learning to Generalize to More:Continuous Semantic Augmentation for Neural Machine Translation | Youtube | |
NLP | Multitask Prompted Training Enables Zero-Shot Task | Youtube | |
NLP | Efficient Passage Retrieval with Hashing for Open-domain Question Answering(BPR) | Youtube | |
NLP | LORA: LOW-RANK ADAPTATION OF LARGE LANGUAGE MODELS | Youtube | |
NLP | Weakly-supervised Text Classification Based on Keyword Graph | Youtube | |
NLP | Improving the Quality Trade-Off for Neural Machine Translation Multi-Domain Adaptation | Youtube | |
NLP | AEDA: An Easier Data Augmentation Technique for Text Classification | Youtube | |
NLP | GTRANS-Grouping and Fusing Transformer Layers for Neural Machine Translation | Youtube | |
NLP | SPLADE : Sparse Lexical and Expansion Model for First Stage Ranking | Youtube | |
NLP | Debiased Contrastive learning of Unsupervised Sentence Representation | Youtube | |
NLP | Calibrating Sequence Likelihood Improves Conditional Language Generation | Youtube | |
NLP | CHAIN-OF-THOUGHT PROMPTING ELICITS REASONING IN LARGE LANGUAGE MODELS | Youtube | |
NLP | A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction | Youtube | |
NLP | Improving Neural Machine Translation with Soft Template Prediction | Youtube | |
NLP | Minerva - Solving Quantitative Reasoning Problems with Language Models | Youtube | |
NLP | PaLM: Scaling Language Modeling with Pathways | Youtube | |
NLP | Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning | Youtube | |
NLP | Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond | Youtube | |
NLP | BRIO: Bringing Order to Abstractive SummarizationS | Youtube | |
NLP | Towards Robust and Reproducible Active Learning using Neural Networks | Youtube | |
NLP | Scaling Instruction-Finetuned Language Models | Youtube | |
NLP | Packed Levitated Marker for Entity and Relation Extraction | Youtube | |
NLP | LLaMA Review! | Youtube | |
NLP | P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks | Youtube | |
NLP | MCSE:Multimodal Contrastive Learning of Sentence Embeddings | Youtube | |
NLP | Hyperbolic Image Embeddings | Youtube | |
NLP | LIMA Less Is More for Alignment | Youtube | |
NLP | Instruct GPT : Training language models to follow instructions with human feedback | Youtube | |
NLP | Iter-RetGen : Enhancing Retrieval augmented Large Language Models with Iterative Retrieval | Youtube | |
NLP | Textbooks Are All You need | Youtube | |
NLP | Embedding Text in Hyperbolic space | Youtube | |
NLP | OpineSum : Entailment based self training for abstractive opinion summarization | Youtube | |
NLP | Do Androids Laugh at Electric Sheep Humor “Understanding” Benchmarks from The New Yorker Caption | Youtube | |
Vision | YOLO | Youtube paper |
Object detection |
Vision | YOLO-v2 | Youtube | Object detection |
Vision | Resnet | Youtube paper |
Image classification |
Vision | GAN | Youtube | Generative Adversarial Networks, Generative Models |
Vision | Image Style Transfer Using CNN | Youtube | Convolutional Neu- ral Network |
Vision | SINGAN | Youtube | Image Generation, Image Manipulation |
Vision | FCN | Youtube | Semantic Segmentation Models |
Vision | DeepLabV3 | Youtube | Semantic Segmentation Models |
Vision | Unet | Youtube paper |
Cell Segmentation, Multi-tissue Nucleus Segmentation |
Vision | CyCADA | Youtube | Domain Adaptation, Semantic Segmentation |
Vision | D-SNE | Youtube | Domain Adaptation |
Vision | Faster-RCNN | Youtube | Real-Time Object Detection, Region Proposal |
Vision | Weakly Supervised Object Detection With Segmentation Collaboration | Youtube | General Classification, Image Classification |
Vision | Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias | Youtube | object classification |
Vision | data efficient image recognition with contrastive predictive coding | Youtube | General Classification, Object Detection |
Vision | Deep Feature Consistent Variational Autoencoder | Youtube | Style Transfer |
Vision | Attention Branch Network: Learning of Attention Mechanism for Visual Explanation | Youtube | Decision Making, Image Classification |
Vision | RELATION-SHAPE CONVOLUTIONAL NEURAL NETWORK FOR POINT CLOUD ANALYSIS | Youtube | |
Vision | EfficientNet | Youtube | |
Vision | Deep Clustering for Unsupervised Learning of Visual Features | Youtube | Deep Clustering, Image Clustering |
Vision | Boosting Few-shot visual learning with self-supervision | Youtube | Few-Shot Learning, Self-Supervised Learning |
Vision | Rethinking Pre-training and Self-training | Youtube | Data Augmentation, Object Detection |
Vision | BYOL : Bootstrap Your Own Latent | Youtube | Representation Learning, Self-Supervised Image Classification |
Vision | Deep Image Prior | Youtube | Image Denoising, Image Inpainting |
Vision | Object-Centric Learning with Slot Attention | Youtube | Object Discovery |
Vision | Yolo V4 | Youtube | Data Augmentation, Real-Time Object Detection |
Vision | Dynamic Routing Between Capsules | Youtube | Image Classification |
Vision | Semi-Supervised Classification with Graph Convolutional Network | Youtube | Classification, Document Classification |
Vision | Generative Pretraining from Pixels | Youtube | Representation Learning, Self-Supervised Image Classification |
Vision | MaskFlownet | Youtube | Feature Matching |
Vision | Adversarial Robustness through Local Linearization | Youtube | Adversarial Defense, Adversarial Robustness |
Vision | Locating Objects Without Bounding Boxes | Youtube | Object Localization |
Vision | Training data-efficient image transformers & distillation through attention | Youtube | Document Image Classification, Document Layout Analysis |
Vision | What Makes Training Multi-modal Classification Networks Hard? | Youtube | Action Classification, Action Recognition |
Vision | Meta-Transfer Learning for Zero-Shot Super-Resolution | Youtube | Image Super-Resolution, Meta-Learning |
Vision | Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation | Youtube | Anomaly Detection, Self-Supervised Learning |
Vision | Style GAN | Youtube | Disentanglement, Image Generation |
Vision | High-Performance Large-Scale Image Recognition Without Normalization | Youtube | Image Classification |
Vision | Focal Loss for Dense Object Detection | Youtube | |
Vision | Editing in Style : Uncovering the Local Semantics of GANs | Youtube | Dense Object Detection, Long-tail Learning |
Vision | EfficientNet 2 | Youtube | Convolutional Neural Networks, Image Models |
Vision | Style Clip | Youtube | Image Manipulation |
Vision | Swin Transformer | Youtube | Image Models, Vision Transformers |
Vision | NBDT: Neural-backed Decision Tree | Youtube | Neural-Backed Decision Trees |
Vision | EfficientDet | Youtube | Semantic Segmentation Models, One-Stage Object Detection Models, Object Detection Models |
Vision | MLP - MIXER: An all-MLP Architecture for Vision | Youtube | Image Classification |
Vision | You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection | Youtube | Object Detection |
Vision | Hierarchical Long-term Video Frame Prediction without Supervision | Youtube | Video Prediction |
Vision | Closed-Form Factorization of Latent Semantics in GANs | Youtube | Image Generation, Image Manipulation |
Vision | You Only Learn One Representation: Unified Network for Multiple Tasks | Youtube | Multi-Task Learning, Real-Time Object Detection |
Vision | StyleSpace Analysis | Youtube | Image Generation |
Vision | Representative graph neural network | Youtube | Representative Graph, Dynamic Sampling, Semantic Segmentation |
Vision | YOLOX | Youtube | One-Stage Object Detection Models |
Vision | Joint Contrastive Learning with Infinite Possibilities | Youtube | Contrastive Learning |
Vision | Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation | Youtube | Image Classification, Neural Architecture Search |
Vision | Explaining in style training a gan to explain a classifier in stylespace | Youtube | Image Classification |
Vision | End-to-End Semi-Supervised Object Detection with Soft Teacher | Youtube | Instance Segmentation, Object Detection |
Vision | Understanding Dimensional Collapse in Contrastive Self Supervised Learning | Youtube | Contrastive Learning, Learning Theory |
Vision | Encoding in Style: a Style Encoder for Image-to-Image Translation | Youtube | Conditional Image Generation, Face Generation |
Vision | Detection in Crowded Scenes: One Proposal, Multiple Predictions | Youtube | Object Detection, Pedestrian Detection |
Vision | A Normalized Gaussian Wasserstein Distance for Tiny Object Detection | Youtube | Object Detection |
Vision | Siamese Neural network for one-shot image recognition | Youtube | One-Shot Learning |
Vision | Grounded Language-Image Pre-training | Youtube | Object Detection Phrase Grounding |
Vision | Transfer Learning for Pose Estimation of Illustrated Characters | Youtube | Activity Recognition, Pose Estimation |
Vision | Sparse R-CNN: End-to-End Object Detection with Learnable Proposals | Youtube | Object Detection, Object Recognition |
Vision | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | Youtube | Neural Rendering, Novel View Synthesis |
Vision | HRnet: Deep High-Resolution Representation Learning for Human Pose Estimation | Youtube | |
Vision | MobileViT : Light-weight, general-purpose, and Mobile-friendly Vision Transformer | Youtube | |
Vision | Effectively Leveraging Attributes for Visual Similarity | Youtube | |
Vision | Hard Negative Mixing for Contrastive learning | Youtube | |
Vision | HOTR : Human-Object Interaction Detection with Transformer | Youtube | |
Vision | SSD: A UNIFIED FRAMEWORK FOR SELF-SUPERVISED OUTLIER DETECTION | Youtube | |
Vision | StyleHEAT : One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN | Youtube | |
Vision | Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut | Youtube | |
Vision | Transfusion: Understanding Transfer Learning for Medical Imaging | Youtube | |
Vision | UCTransNet | Youtube | |
Vision | A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation | Youtube | |
Vision | Vision Transformer with Deformable Attention | Youtube | |
Vision | More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity | Youtube | |
Vision | PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection | Youtube | |
Vision | MetaFormer is Actually What You Need for Vision | Youtube | |
Vision | An Image is Worth 16x16 Words:Transformers for Image Recognition at Scale | Youtube | |
Vision | BigDatasetGAN: Synthesizing ImageNet with Pixel-wise Annotations | Youtube | |
Vision | High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion) | Youtube | |
Vision | Proper Reuse of Image Classification Features Improves Object Detection | Youtube | |
Vision | Voxel Field Fusion for 3D Object Detection | Youtube | |
Vision | MedSefDiff: Medical Image Segmentation with Diffusion Probabilistic Model | Youtube | |
Vision | Pix2Seq | Youtube | |
Vision | Self-Supervised Learning based on Heat Equation | Youtube | |
Vision | Cliff Diving : Exploring Reward Surfaces in Reinforcement Learning Environments | Youtube | |
Vision | WHAT DO VISION TRANSFORMERS LEARN?A VISUAL EXPLORATION | Youtube | |
Vision | InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions | Youtube | |
Vision | Cut and Learn for Unsupervised Object Detection and Instance Segmentation | Youtube | |
Vision | The Forward-Forward Algorithm: Some Preliminary Investigations | Youtube | |
Vision | Visual Prompt Tuning | Youtube | |
Vision | Dataset Distillation by Matching Training Trajectories | Youtube | |
Vision | YOLO v6 | Youtube | |
Vision | InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning | Youtube | |
Vision | ImageBind One Embedding Space To Bind Them All | Youtube | |
Vision | Learning to Generate Text grounded Mask for Open world Semantic Segmentation from Only Image-Text Pairs | Youtube | |
Vision | Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold | Youtube | |
Vision | Segment Anything in High Quality | Youtube | |
Vision | Multi Domain Learning for Motion Magnification | Youtube | |
Vision | 3D Gaussian Splatting for Real Time Radiance Field Rendering | Youtube | |
Vision | VoxelNet End-to-End Learning for Point Cloud Based 3D Object Detection | Youtube | |
Vision | DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation | Youtube | |
Vision | MIC Masked Image Consistency for Context Enhanced Domain Adaptation | Youtube | |
Recommend System | Matrix Factorization Technique for Recommender System | Youtube paper |
Recommendation system |
Recommend System | Collaborative Filtering for Implicit Feedback Dataset | Youtube | recommender systems, Collaborative Filtering |
Speech | A comparison of S2S models for speech recognition | Youtube paper |
Speech Recognition |
Fundamental | RAdam | Youtube blog paper |
Regularization, Stochastic Optimization |
Fundamental | Stacked Auto Encoder for the P300 Component Detection | Youtube | brain-computer interfaces |
Fundamental | A survey on Image Data Augmentation for DL | Youtube paper |
Data augmentation, 3D Human Pose Estimation |
Fundamental | Training Confidence-calibrated classifiers for detecting out of distribution samples | Youtube | classifiers |
Fundamental | AdamW | Youtube blog |
stochastic optimization |
Fundamental | Stargan | Youtube | Image-to-Image Translation, Translation |
Fundamental | Drop-out | Youtube | Dropout, Data augmentation |
Fundamental | BLEU: a Method for Automatic Evaluation of Machine Translation | Youtube | evaluation |
Fundamental | t-SNE | Youtube | Dimensionality Reduction |
Fundamental | Gpipe | Youtube | Synchronous Pipeline Parallel, Model Parallel Methods |
Fundamental | explainable ai | Youtube | interpretability, sensitivity analysis |
Fundamental | TAPAS | Youtube | Deep Tabular Learning, Table Question Answering Models |
Fundamental | Learning both Weights and Connections for Efficient Neural Networks | Youtube | Neural networks |
Fundamental | ReVACNN | Youtube | Visualization, Convolutional Neural Network |
Fundamental | The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks | Youtube | Network Pruning |
Fundamental | ALPHAGO : Mastering the game of Go with Deep Neural Networks and Tree Search | Youtube | deep neural networks, tree search |
Fundamental | A Baseline for Few-Shot Image Classification | Youtube | FEW-SHOT IMAGE CLASSIFICATION |
Fundamental | Sharp Minima Can Generalize For Deep Nets | Youtube | deep learning architectures |
Fundamental | Pediatric Sleep Stage Classification Using Multi-Domain Hybrid Neural Networks | Youtube | Multi-Domain Hybrid Neural Networks |
Fundamental | Pruning from Scratch | Youtube | Network Pruning |
Fundamental | Do We Need Zero Training Loss After Achieving Zero Training Error? | Youtube | Training Loss |
Fundamental | Deep Recurrent Q-Learning for Partially Observable MDPs | Youtube | Atari Games, OpenAI Gym |
Fundamental | Large Margin Deep Networks for Classification | Youtube | Classification, Data Augmentation |
Fundamental | generating wikipedia by summarizing long sequences | Youtube | Document Summarization, Extractive Summarization |
Fundamental | Plug and Play Language Models: A Simple Approach to Controlled Text Generation | Youtube | Language Modelling, Text Generation |
Fundamental | What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? | Youtube | Depth Estimation, Semantic Segmentation |
Fundamental | KRED | Youtube | Entity Embeddings, News Recommendation |
Fundamental | Early Stopping as nonparametric Variational | Youtube | Variational Inference |
Fundamental | Sharpness Aware Minimization for efficeintly improving generalization | Youtube | GENERALIZATION |
Fundamental | Neural Graph Collaborative Filtering | Youtube | Collaborative Filtering, Link Prediction |
Fundamental | Restricting the Flow: Information Bottlenecks for Attribution | Youtube | Decision Making |
Fundamental | Real world Anomaly Detection in Surveillance Videos | Youtube | Activity Recognition, Anomaly Detection In Surveillance Videos |
Fundamental | BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction | Youtube | Image Classification Object Detection |
Fundamental | Deep sets (2017 NIPS) | Youtube | designing models |
Fundamental | StyleGAN2 | Youtube | Generative Adversarial Networks, Generative Models |
Fundamental | Beyond Synthetic Noise: Deep Learning on Controlled Noisy Labels | Youtube | Image Classification |
Fundamental | Deep Reinforcement Learning for Online Advertising Impression in Recommender Systems | Youtube | Recommendation Systems |
Fundamental | Longformer: The Long-Document Transformer | Youtube | Language Modelling, Question Answering |
Fundamental | soft actor critic | Youtube | Policy Gradient Methods |
Fundamental | Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search | Youtube | Object Detection |
Fundamental | The Deep Bootstrap Framework: Good Online Learners are Good Offline Generalizers | Youtube | Image Classification, online learning |
Fundamental | Meta HIN | Youtube | Social and Information Networks |
Fundamental | When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations | Youtube | Domain Generalization, Fine-Grained Image Classification |
Fundamental | Self similarity Student for Partial Label Histopathology Image Segmentation | Youtube | Semantic Segmentation, whole slide images |
Fundamental | ANALYSING MATHEMATICAL REASONING ABILITIES OF NEURAL MODELS | Youtube | Mathematical Reasoning, Math Word Problem Solving |
Fundamental | Self-training Improves Pre-training for Natural Language Understanding | Youtube | Data Augmentation, Few-Shot Learning |
Fundamental | Preference Amplification in Recommender Systems | Youtube | Recommender Systems |
Fundamental | Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation | Youtube | Partial Domain Adaptation, Representation Learning |
Fundamental | Evaluating Classifiers by Means of Test Data with Noisy Labels | Youtube | Evaluating Classifiers |
Fundamental | Progressive Identification of True Labels for Partial-Label Learning | Youtube | Partial Label Learning, Stochastic Optimization |
Fundamental | Fine-grained Interest Matching For Neural News Recommendation | Youtube | News Recommendation |
Fundamental | Adversarial Reinforced Learning for Unsupervised Domain Adaptation | Youtube | Transfer Learning |
Fundamental | Neural Tangent Kernel - Convergence and Generalization in neural Network | Youtube | Gaussian Processes |
Fundamental | Intriguing Properties of Contrastive Losses | Youtube | Contrastive Learning, Data Augmentation |
Fundamental | Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets | Youtube | Overfitting |
Fundamental | Transformer Interpretability Beyond Attention Visualization | Youtube | Classification, General Classification |
Fundamental | How does unlabeled data improve generalization in self-training? | Youtube | semi-supervised learning algorithm |
Fundamental | Rainbow: Combining Improvements in Deep Reinforcement Learning | Youtube | Montezuma's Revenge |
Fundamental | Once-for-All: Train One Network and Specialize it for Efficient Deployment | Youtube | |
Fundamental | Effective Diversity in Population Based Reinforce Learning | Youtube | |
Fundamental | Fine-Tuning can Distort Pretrained Features and Under perform Out-of-Distribution | Youtube | |
Fundamental | GCN-LRP explanationexploring latent attention of graph convolutional networks | Youtube | |
Fundamental | Towards Safe Online Reinforced Learning in Computer Systems | Youtube | |
Fundamental | Conflict-Averse Gradient Descent for Multi-task Learning | Youtube | |
Fundamental | Explainability Methods for Graph Convolutional Neural Networks | Youtube | |
Fundamental | Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning | Youtube | |
Fundamental | Efficiently Identifying Task Grouping for Multi-Task Learning | Youtube | |
Fundamental | DeepFM: A Factorization-Machine based Neural Network for CTR Prediction | Youtube | |
Fundamental | Deep Neural Networks for YouTube Recommendations | Youtube | |
reinforcement learning | Deep reinforcement learning from human preferences | Youtube | |
reinforcement learning | Distributional Reinforcement Learning via Moment Matching | Youtube | |
reinforcement learning | Online Continual Learning on class Incremental Blurry Task Configuration with anytime inference | Youtube | |
reinforcement learning | Dream To Control : Learning Behaviors by Latent Imagination | Youtube | |
reinforcement learning | Proximal Policy Optimization Algorithms | Youtube | |
reinforcement learning | Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs | Youtube | |
reinforcement learning | VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning | Youtube | |
reinforcement learning | mPLUG: Effective and Efficient Vision-Language Learning byCross-modal Skip-connections | Youtube | |
reinforcement learning | MOReL: Model-Based OfflineReinforcement Learning | Youtube | |
reinforcement learning | RL upside down | Youtube | |
reinforcement learning | Trans Dreamer | Youtube | |
reinforcement learning | Trajectory Transformer | Youtube | |
reinforcement learning | Addressing Optimism Bias in Sequence Modeling for RL | Youtube |