lzhxmu / CPPOLinks
CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
☆138Updated 3 weeks ago
Alternatives and similar repositories for CPPO
Users that are interested in CPPO are comparing it to the libraries listed below
Sorting:
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆131Updated 2 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆222Updated last month
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆191Updated last week
- ☆203Updated 4 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆240Updated 3 weeks ago
- ✨✨R1-Reward: Training Multimodal Reward Model Through Stable Reinforcement Learning☆150Updated last month
- ☆220Updated last month
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆130Updated 2 months ago
- ☆303Updated 2 weeks ago
- MMR1: Advancing the Frontiers of Multimodal Reasoning☆160Updated 3 months ago
- ☆300Updated 3 weeks ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆104Updated last month
- ☆85Updated last week
- Official code for the paper, "Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning"☆125Updated last week
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆156Updated 3 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆144Updated 6 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆73Updated 4 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆113Updated 2 months ago
- ☆241Updated 2 weeks ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆94Updated 3 months ago
- 😎 A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond☆252Updated 2 weeks ago
- ☆222Updated last week
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆275Updated 3 weeks ago
- ☆116Updated last month
- [ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation☆105Updated last month
- Repo of paper "Free Process Rewards without Process Labels"☆153Updated 3 months ago
- A version of verl to support tool use☆261Updated this week
- Paper collections of multi-modal LLM for Math/STEM/Code.☆101Updated this week
- One-shot Entropy Minimization☆149Updated 2 weeks ago
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆123Updated 2 months ago