GitHub

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. [arXiv:2510.06261] "AlphaApollo: A System for Deep Agentic Reasoning"

    Python 50 12

  2. [ICML 2026] "The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning"

    Python 3

  3. [ICML 2026] "Concept Concentration for Faithful Representation Intervention"

    Python 1

  4. Forked from resistzzz/Co-rewarding

    [ICLR 2026] "Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models"

    Python 58 1

  5. Forked from junnie00/ConV

    [NeurIPS 2025 Spotlight] "Detecting Generated Images by Fitting Natural Image Distributions"

    Python 13

  6. [NeurIPS 2025] "Generative Model Inversion Through the Lens of the Manifold Hypothesis"

    Python 5

Repositories

Showing 10 of 128 repositories

  • AlphaDiana Public

    AlphaDiana: A System for Evaluating Agentic Reasoning

    tmlr-group/AlphaDiana's past year of commit activity

    Python

    22 1 0 0

    Updated Aug 12, 2026

  • tmlr-group/tmlr-group.github.io's past year of commit activity

    HTML

    0 0 0 0

    Updated Aug 11, 2026

  • TADS Public Forked from haochenglouis/TADS

    [ICLR 2026] "Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM Finetuning"

    tmlr-group/TADS's past year of commit activity

    Python

    1 1 0 0

    Updated Jul 14, 2026

  • USAD Public Forked from yeager20001118/USAD

    [ICML 2026 workshop] Code repository for USAD: Uncertainty-aware Statistical Adversarial Detection

    tmlr-group/USAD's past year of commit activity

    Python

    0 1 0 0

    Updated Jun 23, 2026

  • CoDaPO Public

    [ICML 2026] "The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning"

    tmlr-group/CoDaPO's past year of commit activity

    Python

    3

    Apache-2.0

    0 0 0

    Updated Jun 19, 2026

  • RewardFlow Public

    [arXiv:2603.18859] "RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models"

    tmlr-group/RewardFlow's past year of commit activity

    Python

    13

    Apache-2.0

    0 0 0

    Updated Jun 5, 2026

  • COCA Public

    [ICML 2026] "Concept Concentration for Faithful Representation Intervention"

    tmlr-group/COCA's past year of commit activity

    Python

    1

    Apache-2.0

    0 0 0

    Updated May 28, 2026

  • AMD Public Forked from zhijianzhouml/AMD

    Reproducibility code for AMD: Anchor-based Maximum Discrepancy for Relative Similarity Testing

    tmlr-group/AMD's past year of commit activity

    Python

    0

    MIT

    1 0 0

    Updated May 27, 2026

  • tmlr-group/NAMMD's past year of commit activity

    Python

    0 2 0 0

    Updated May 27, 2026

  • AgentHijack Public Forked from super-jw/AgentHijack

    [ICML 2026] "AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions"

    tmlr-group/AgentHijack's past year of commit activity

    Python

    6 1 0 0

    Updated May 27, 2026

Read the original on github.com ↗