GAIR-NLP / MAYELinks
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
☆146Updated 9 months ago
Alternatives and similar repositories for MAYE
Users that are interested in MAYE are comparing it to the libraries listed below
Sorting:
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆154Updated last week
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 7 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆330Updated 7 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆191Updated 9 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆163Updated 3 months ago
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources☆212Updated 3 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆171Updated 2 months ago
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆169Updated 3 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆174Updated 7 months ago
- "what, how, where, and how well? a survey on test-time scaling in large language models" repository☆83Updated this week
- 🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…☆191Updated last month
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆57Updated last year
- A RLHF Infrastructure for Vision-Language Models☆191Updated last year
- Extrapolating RLVR to General Domains without Verifiers☆187Updated 5 months ago
- [ICCV 2025 Highlight] The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"☆187Updated 9 months ago
- 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…☆380Updated 4 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆94Updated 7 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆213Updated 4 months ago
- ☆109Updated last year
- Towards a Unified View of Large Language Model Post-Training☆199Updated 4 months ago
- [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback☆301Updated last year
- [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆300Updated 4 months ago
- ☆208Updated 2 months ago
- [Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆523Updated last week
- Paper collections of multi-modal LLM for Math/STEM/Code.☆134Updated last month
- A set of examples based on verl for end-to-end RL training recipes.☆108Updated this week
- [NeurIPS 2024] MATH-Vision dataset and code to measure multimodal mathematical reasoning capabilities.☆128Updated 7 months ago
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆348Updated 3 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆120Updated last year
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆191Updated last month