Skip to content
@tmlr-group

TMLR Group

Trustworthy Machine Learning and Reasoning Group
README.md

Trustworthy Machine Learning and Reasoning (TMLR) Group, an online-offline-mixed machine learning research group, locates in different cities, including Hong Kong, Melbourne, Shanghai, Nottingham and Sydney. We share the vision for the future ML technology: building trustworthy learning and reasoning algorithms, theories and systems.

Pinned Loading

  1. AR-Bench AR-Bench Public

    [ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"

    Python 43 2

  2. DAD DAD Public

    Forked from JiachengZ01/DAD

    [ICML 2025] "One Stone, Two Birds: Enhancing Adversarial Defense Through the Lens of Distributional Discrepancy"

    Python 2

  3. G-effect G-effect Public

    Forked from QizhouWang/G-effect

    [ICLR 2025] "Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond"

    Python 12 1

  4. AttrVR AttrVR Public

    Forked from caichengyi/AttrVR

    [ICLR 2025] "Attribute-based Visual Reprogramming for Vision-Language Models" Official Website: https://github.com/tmlr-group/AttrVR

    Python 2

  5. NoisyRationales NoisyRationales Public

    [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"

    Python 37 3

  6. BayesianLM BayesianLM Public

    Forked from caichengyi/BayesianLM

    [NeurIPS 2024 Oral] "Bayesian-Guided Label Mapping for Visual Reprogramming"

    Python 11 1

Repositories

Showing 10 of 97 repositories
  • AR-Bench Public

    [ICML 2025] "From Passive to Active Reasoning: Can Large Language Models Ask the Right Questions under Incomplete Information?"

    tmlr-group/AR-Bench’s past year of commit activity
    Python 43 2 1 0 Updated Oct 8, 2025
  • Co-rewarding Public Forked from resistzzz/Co-rewarding

    [arXiv:2508.00410] "Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models"

    tmlr-group/Co-rewarding’s past year of commit activity
    Python 39 4 0 0 Updated Oct 6, 2025
  • NSG-VD Public Forked from ZSHsh98/NSG-VD

    This is the source code for Physics-Driven Spatiotemporal Modeling for AI-Generated Video Detection (NeurIPS 2025).

    tmlr-group/NSG-VD’s past year of commit activity
    Python 0 Apache-2.0 1 0 0 Updated Oct 6, 2025
  • AlphaApollo Public

    [arXiv:2510.06261] "AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning"

    tmlr-group/AlphaApollo’s past year of commit activity
    7 0 0 0 Updated Oct 5, 2025
  • landscape-of-thoughts Public

    [ICLR 2025 Workshop] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"

    tmlr-group/landscape-of-thoughts’s past year of commit activity
    Jupyter Notebook 36 MIT 4 0 0 Updated Aug 16, 2025
  • NoisyRationales Public

    [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"

    tmlr-group/NoisyRationales’s past year of commit activity
    Python 37 3 0 0 Updated Jul 18, 2025
  • ECON Public

    [ICML 2025] "From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibrium"

    tmlr-group/ECON’s past year of commit activity
    Python 25 MIT 1 2 0 Updated Jul 10, 2025
  • SatImp Public

    [ICML 2025] "Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning"

    tmlr-group/SatImp’s past year of commit activity
    Python 0 0 0 0 Updated Jul 6, 2025
  • GRU Public

    [ICML 2025] "GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs"

    tmlr-group/GRU’s past year of commit activity
    Python 1 1 0 0 Updated Jul 5, 2025
  • BiDO_plus Public

    [TPAMI 2025] "Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks"

    tmlr-group/BiDO_plus’s past year of commit activity
    Python 0 MIT 0 0 0 Updated Jun 17, 2025
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.