InternLM / OREALLinks
Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
☆188Updated 4 months ago
Alternatives and similar repositories for OREAL
Users that are interested in OREAL are comparing it to the libraries listed below
Sorting:
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆140Updated 3 weeks ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆138Updated 3 months ago
- ☆205Updated 5 months ago
- OpenRFT: Adapting Reasoning Foundation Model for Domain-specific Tasks with Reinforcement Fine-Tuning☆146Updated 7 months ago
- xVerify: Efficient Answer Verifier for Reasoning Model Evaluations☆125Updated 3 months ago
- ☆258Updated 2 months ago
- Official Repository of "Learning to Reason under Off-Policy Guidance"☆268Updated 2 weeks ago
- ☆306Updated 2 months ago
- ☆322Updated this week
- A version of verl to support tool use☆312Updated this week
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆138Updated 3 months ago
- L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning☆232Updated 2 months ago
- A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.☆245Updated 3 months ago
- Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆80Updated last month
- ☆196Updated 3 months ago
- Repo of paper "Free Process Rewards without Process Labels"☆160Updated 4 months ago
- The Entropy Mechanism of Reinforcement Learning for Large Language Model Reasoning.☆275Updated 3 weeks ago
- A Comprehensive Survey on Long Context Language Modeling☆166Updated 3 weeks ago
- Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".☆101Updated 2 weeks ago
- ☆157Updated 3 months ago
- ☆64Updated 8 months ago
- repo for paper https://arxiv.org/abs/2504.13837☆180Updated last month
- ☆195Updated this week
- ☆293Updated last month
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆105Updated 2 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models☆145Updated last month
- A highly capable 2.4B lightweight LLM using only 1T pre-training data with all details.☆200Updated last week
- A visuailzation tool to make deep understaning and easier debugging for RLHF training.☆238Updated 5 months ago
- A light-weight tool for evaluating LLMs in rule-based ways.☆66Updated last month
- MMSearch-R1 is an end-to-end RL framework that enables LMMs to perform on-demand, multi-turn search with real-world multimodal search too…☆268Updated last month