Skip to content
Change the repository type filter

All

    Repositories list

    • [arXiv:2603.18859] "RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models"
      Python
      Apache License 2.0
      01000Updated Jun 5, 2026Jun 5, 2026
    • CoDaPO

      Public
      [ICML 2026] "The Easy, the Hard, and the Learnable: Confidence and Difficulty-Adaptive Policy Optimization for LLM Reasoning"
      Python
      Apache License 2.0
      0100Updated May 31, 2026May 31, 2026
    • COCA

      Public
      [ICML 2026] "Concept Concentration for Faithful Representation Intervention"
      Python
      Apache License 2.0
      0000Updated May 28, 2026May 28, 2026
    • AMD

      Public
      Reproducibility code for AMD: Anchor-based Maximum Discrepancy for Relative Similarity Testing
      Python
      MIT License
      1000Updated May 27, 2026May 27, 2026
    • [ICML 2026] "AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions"
      Python
      1500Updated May 27, 2026May 27, 2026
    • [ICLR 2026] "Landscape of Thoughts: Visualizing the Reasoning Process of Large Language Models"
      Jupyter Notebook
      MIT License
      76000Updated May 21, 2026May 21, 2026
    • TriMem

      Public
      [arXiv:2605.19952] "Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory"
      Python
      MIT License
      01400Updated May 20, 2026May 20, 2026
    • [arXiv:2510.06261] "AlphaApollo: A System for Deep Agentic Reasoning"
      Python
      Apache License 2.0
      84510Updated May 18, 2026May 18, 2026
    • JavaScript
      0000Updated May 5, 2026May 5, 2026
    • MAD-MM

      Public
      [ICLR 2026] "Multi-Agent Debate with Memory Masking"
      Python
      31000Updated Apr 21, 2026Apr 21, 2026
    • TADS

      Public
      [ICLR 2026] "Task-Aware Data Selection via Proxy-Label Enhanced Distribution Matching for LLM Finetuning"
      Python
      1100Updated Apr 17, 2026Apr 17, 2026
    • CARPRT

      Public
      [ICLR 2026] "CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models"
      Python
      1200Updated Apr 8, 2026Apr 8, 2026
    • A System for Evaluating Reasoning Agents such as OpenClaw
      Python
      12000Updated Apr 3, 2026Apr 3, 2026
    • [ICLR 2026] "JailbreakLoRA: Your Downloaded LoRA from Sharing Platforms Might Be Unsafe"
      Python
      MIT License
      1200Updated Mar 21, 2026Mar 21, 2026
    • RePO

      Public
      [ICLR 2026] "Reference-guided Policy Optimization for Molecular Optimization via LLM Reasoning"
      Python
      1800Updated Mar 19, 2026Mar 19, 2026
    • LoT-2026

      Public
      [ICLR 2026] "On the Thinking-Language Modeling Gap in Large Language Models"
      Python
      1200Updated Mar 3, 2026Mar 3, 2026
    • TARF

      Public
      [ICLR 2026] "Decoupling the Class Label and the Target Concept in Machine Unlearning"
      Python
      MIT License
      1200Updated Feb 27, 2026Feb 27, 2026
    • [ICLR 2026] "Towards Understanding Valuable Preference Data for Large Languge Model Alignment"
      Shell
      1100Updated Feb 23, 2026Feb 23, 2026
    • BITTA

      Public
      [ICLR 2026] "Bilateral Information-aware Test-time Adaptation for Vision-Language Models"
      Python
      MIT License
      1300Updated Feb 13, 2026Feb 13, 2026
    • SAFT

      Public
      [TMLR 2026] "Semantic-aware Adversarial Fine-tuning for CLIP"
      Python
      MIT License
      1000Updated Feb 9, 2026Feb 9, 2026
    • [ICLR 2026] "Beyond Raw Detection Scores: Markov-Aware Calibration for Boosting Machine-Generated Text Detection"
      Python
      MIT License
      2000Updated Feb 7, 2026Feb 7, 2026
    • [ICLR 2026] "Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models"
      Python
      45700Updated Feb 4, 2026Feb 4, 2026
    • WePe

      Public
      [NeurIPS 2025] "Epistemic Uncertainty for Generated Image Detection"
      Python
      MIT License
      1100Updated Feb 3, 2026Feb 3, 2026
    • BiFTA

      Public
      [TMLR 2026] "Let's Roll a BiFTA: Bi-refinement for Fine-grained Text-visual Alignment in Vision-Language Models"
      Python
      1100Updated Jan 25, 2026Jan 25, 2026
    • [TPAMI 2026] "Co-Boosting++: Coupled Optimization of Data and Ensemble for One-Shot Federated Learning"
      Python
      1000Updated Jan 11, 2026Jan 11, 2026
    • IFR

      Public
      [IJCV 2025] "Cross-domain Few-shot Classification via Invariant-content Feature Reconstruction"
      Python
      1000Updated Jan 2, 2026Jan 2, 2026
    • SFAT-Star

      Public
      [TPAMI 2025] "Slack Federated Adversarial Training"
      Python
      MIT License
      1100Updated Dec 28, 2025Dec 28, 2025
    • [NeurIPS 2025] "DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing"
      Python
      MIT License
      1100Updated Dec 22, 2025Dec 22, 2025
    • SatImp

      Public
      [ICML 2025] "Exploring Criteria of Loss Reweighting to Enhance LLM Unlearning"
      Python
      0100Updated Dec 19, 2025Dec 19, 2025
    • ConV

      Public
      [NeurIPS 2025 Spotlight] "Detecting Generated Images by Fitting Natural Image Distributions"
      Python
      MIT License
      11200Updated Dec 18, 2025Dec 18, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.