Skip to content

@Qwen-Applications Qwen Applications Business Group

Change the repository type filter

All

    Repositories list

    11 repositories

    • RiT

      Public
      RiT: Rubrics-in-Thinking Reinforcement Learning for Improved Reasoning in Large Language Models
      Apache License 2.0
      •0•0•0•0•Updated Apr 15, 2026Apr 15, 2026

    • CLIPO

      Public
      CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
      reasoningcontrastive-learninglarge-language-models
      reasoningcontrastive-learninglarge-language-modelsrlvr
      Python
      •2•19•1•0•Updated Apr 7, 2026Apr 7, 2026

    • ATP-Bench

      Public
      0•2•2•0•Updated Mar 30, 2026Mar 30, 2026

    • MARCH

      Public
      4•22•1•1•Updated Mar 26, 2026Mar 26, 2026

    • STAR

      Public
      STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models
      knowledge-distillationreinforcment-learningllm
      knowledge-distillationreinforcment-learningllmfunction-callingtiny-llm
      Python
      •
      Apache License 2.0
      •0•44•0•0•Updated Mar 23, 2026Mar 23, 2026

    • Proxy-GRM

      Public
      Python
      •
      Apache License 2.0
      •0•4•2•0•Updated Mar 19, 2026Mar 19, 2026

    • EVPV-PRM

      Public
      Python
      •
      Apache License 2.0
      •0•7•0•0•Updated Mar 19, 2026Mar 19, 2026

    • OpenRS

      Public
      Open Rubric System: Scaling Reinforcement Learning with Pairwise Adaptive Rubric
      rubricrlhfreward-model
      rubricrlhfreward-model
      Python
      •
      Apache License 2.0
      •1•10•1•0•Updated Mar 5, 2026Mar 5, 2026

    • SiameseNorm

      Public
      Code of the research paper "SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm"
      Python
      •751•8•0•0•Updated Feb 27, 2026Feb 27, 2026

    • DIR

      Public
      Python
      •
      Apache License 2.0
      •1•17•1•0•Updated Feb 14, 2026Feb 14, 2026

    • SSP

      Public
      Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
      Python
      •
      Apache License 2.0
      •8•17•0•0•Updated Dec 30, 2025Dec 30, 2025
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.