TMLR Group

Trustworthy Machine Learning and Reasoning Group

Hong Kong

Pinned Repositories

AR-Bench
[ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"
Language:Python373
AttrVR
[ICLR 2025] "Attribute-based Visual Reprogramming for Vision-Language Models" Official Website: https://github.com/tmlr-group/AttrVR
Language:Python2 0 00
BayesianLM
[NeurIPS 2024 Oral] "Bayesian-Guided Label Mapping for Visual Reprogramming"
Language:Python11 0 01
Co-rewarding
[arXiv:2508.00410] "Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement"
Language:Python371
DAD
[ICML 2025] "One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy"
Language:Python20
DeepInception
[arXiv:2311.03191] "DeepInception: Hypnotize Large Language Model to Be Jailbreaker"
Language:Python162 4 020
G-effect
[ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"
Language:Python121
landscape-of-thoughts
[ICLR 2025 Workshop] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"
Language:Jupyter Notebook352
NoisyRationales
[NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"
Language:Python37 4 02
WCA
[ICML 2024] "Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models"
Language:Python56 0 03

TMLR Group's Repositories

tmlr-group/AR-Bench
[ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"
Language:Python373
tmlr-group/Co-rewarding
[arXiv:2508.00410] "Co-Reward: Self-supervised Reinforcement Learning for Large Language Model Reasoning via Contrastive Agreement"
Language:Python371
tmlr-group/NoisyRationales
[NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"
Language:Python37 4 02
tmlr-group/landscape-of-thoughts
[ICLR 2025 Workshop] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"
Language:Jupyter Notebook352
tmlr-group/ECON
[ICML 2025] "From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium"
Language:Python222
tmlr-group/CausalCOAT
[NeurIPS 2024] "Discovery of the Hidden World with Large Language Models"
Language:Jupyter Notebook21 0 03
tmlr-group/EOE
[ICML 2024] "Envisioning Outlier Exposure by Large Language Models for Out-of-Distribution Detection"
Language:Python12 0 00
tmlr-group/G-effect
[ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"
Language:Python121
tmlr-group/SCT
[NeurIPS 2024] "Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection"
Language:Python12 0 01
tmlr-group/SMM
[ICML 2024 Spotlight] "Sample-specific Masks for Visual Reprogramming-based Prompting"
Language:Python12 0 02
tmlr-group/ZS-NTTA
[ICLR 2025] "Noisy Test-Time Adaptation in Vision-Language Models"
Language:Python12 0 01
tmlr-group/BayesianLM
[NeurIPS 2024 Oral] "Bayesian-Guided Label Mapping for Visual Reprogramming"
Language:Python11 0 01
tmlr-group/CoPA
[NeurIPS 2024] "Mind the Gap between Prototypes and Images in Cross-domain Finetuning"
Language:Jupyter Notebook11 0 0
tmlr-group/FABFlex
[ICLR 2025] "Fast and Accurate Blind Flexible Docking"
Language:Python10 0 0
tmlr-group/PPDG-MI
[NeurIPS 2024] "Pseudo-Private Data Guided Model Inversion Attacks"
Language:Jupyter Notebook3 3 00
tmlr-group/AttrVR
[ICLR 2025] "Attribute-based Visual Reprogramming for Vision-Language Models" Official Website: https://github.com/tmlr-group/AttrVR
Language:Python2 0 00
tmlr-group/DAD
[ICML 2025] "One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy"
Language:Python20
tmlr-group/DecoupledVP
[ICML 2025] "Understanding Model Reprogramming for CLIP via Decoupling Visual Prompts". Official Website: https://github.com/tmlr-group/DecoupledVP
2
tmlr-group/Unlearning-with-Control
[ICLR 2025] "Towards Effective Evaluations and Comparisons for LLM Unlearning Methods"
Language:Python2 4 0
tmlr-group/Awesome-model-inversion-attack
[arXiv:2411.10023] "Model Inversion Attacks: A Survey of Approaches and Countermeasures"
1
tmlr-group/GRU
[ICML 2025] "GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs"
Language:Python1
tmlr-group/HPFL
[ICLR 2025] "Hot-pluggable Federated Learning: Briding General and Personalized FL via Dynamic Selection"
1
tmlr-group/SCIE
[AAAI 2025] "Eliciting Causal Abilities in Large Language Models for Reasoning Tasks"
1
tmlr-group/.github
0 3 00
tmlr-group/BiDO_plus
[TPAMI 2025] "Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks"
Language:Python
tmlr-group/CausalProbe-2024
[NeurIPS 2024] "Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?"
tmlr-group/SatImp
[ICML 2025] "Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning"
Language:Python
tmlr-group/SSNI
[ICML 2025] "Sample-Specific Noise Injection For Diffusion-Based Adversarial Purification"
tmlr-group/tmlr-group.github.io
Language:JavaScript
tmlr-group/W-DOE
[TPAMI 2025] "W-DOE: Wasserstein Distribution-agnostic Outlier Exposure"