Skip to content
Change the repository type filter

All

    Repositories list

    • EasySteer

      Public
      A Unified Framework for High-Performance and Extensible LLM Steering
      Python
      Apache License 2.0
      1518330Updated Mar 6, 2026Mar 6, 2026
    • A curated collection of resources, tools, and frameworks for developing GUI Agents.
      1431300Updated Mar 2, 2026Mar 2, 2026
    • A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Apache License 2.0
      14k001Updated Feb 19, 2026Feb 19, 2026
    • [ICLR 2026] VerifyBench: Benchmarking Reference-based Reward Systems for Large Language Models
      Python
      MIT License
      01900Updated Feb 18, 2026Feb 18, 2026
    • [ICLR 2026] InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models
      Python
      MIT License
      14700Updated Feb 12, 2026Feb 12, 2026
    • InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
      Apache License 2.0
      32510Updated Feb 9, 2026Feb 9, 2026
    • GUI-G2

      Public
      [AAAI 2026] GUI-G²: Gaussian Reward Modeling for GUI Grounding
      Python
      930531Updated Feb 2, 2026Feb 2, 2026
    • [ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
      Python
      07400Updated Jan 29, 2026Jan 29, 2026
    • ViewSpatial-Bench:Evaluating Multi-perspective Spatial Localization in Vision-Language Models
      Python
      Apache License 2.0
      17000Updated Jan 8, 2026Jan 8, 2026
    • a framework for GUI Grounding
      Python
      1400Updated Dec 2, 2025Dec 2, 2025
    • Grounding and Mobile Navigation Demo
      Python
      1000Updated Nov 28, 2025Nov 28, 2025
    • SVGenius

      Public
      [ACM MM 2025] SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation. https://arxiv.org/abs/2506.03139
      Python
      Apache License 2.0
      77520Updated Nov 10, 2025Nov 10, 2025
    • GUI-RCPO

      Public
      [AAAI 2026] Test-Time Reinforcement Learning for GUI Grounding via Region Consistency https://arxiv.org/abs/2508.05615
      Python
      36110Updated Nov 8, 2025Nov 8, 2025
    • SBT

      Public
      JavaScript
      0000Updated Nov 4, 2025Nov 4, 2025
    • [NeurIPS 2025] Let LRMs Break Free from Overthinking via Self-Braking Tuning. https://arxiv.org/abs/2505.14604
      Python
      Apache License 2.0
      05530Updated Nov 4, 2025Nov 4, 2025
    • A high-throughput and memory-efficient inference and serving engine for LLMs
      Python
      Apache License 2.0
      14k100Updated Oct 31, 2025Oct 31, 2025
    • [NeurIPS 2025] Mind the Gap: Bridging Thought Leap for Improved CoT Tuning https://arxiv.org/abs/2505.14684
      Python
      Apache License 2.0
      34500Updated Oct 20, 2025Oct 20, 2025
    • LAPO

      Public
      Python
      Apache License 2.0
      03610Updated Oct 9, 2025Oct 9, 2025
    • GSM8K-V

      Public
      GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual Contexts
      Python
      MIT License
      33900Updated Sep 30, 2025Sep 30, 2025
    • Meta-info of papers from ZJU-REAL
      MIT License
      0000Updated Sep 28, 2025Sep 28, 2025
    • cooper

      Public
      Python
      Apache License 2.0
      02510Updated Aug 19, 2025Aug 19, 2025
    • HBPO

      Public
      Python
      Apache License 2.0
      13210Updated Aug 11, 2025Aug 11, 2025
    • Benchmarking agent reasoning capabilities in physical interactions, tool usage, and multi-agent coordination.
      Python
      MIT License
      24310Updated Aug 10, 2025Aug 10, 2025
    • Python
      MIT License
      1800Updated Jun 27, 2025Jun 27, 2025
    • TimeHC-RL

      Public
      This repository is the official implementation of TimeHC-RL (Distilabel (Data Generation) + TRL (SFT) + VeRL (GRPO)).
      24810Updated Jun 4, 2025Jun 4, 2025
    • JavaScript
      1001Updated May 28, 2025May 28, 2025
    • JavaScript
      1101Updated May 24, 2025May 24, 2025