GAIR-NLP / MAYELinks
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
☆142Updated 6 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.☆147Updated 2 weeks ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆189Updated 7 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆319Updated 4 months ago
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 4 months ago
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources☆203Updated 3 weeks ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆158Updated last month
- GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆167Updated last week
- 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…☆335Updated last month
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆154Updated last week
- "what, how, where, and how well? a survey on test-time scaling in large language models" repository☆73Updated this week
- 🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…☆185Updated last week
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆157Updated 4 months ago
- [ICCV 2025 Highlight] The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"☆173Updated 7 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆85Updated 5 months ago
- MiroMind-M1 is a fully open-source series of reasoning language models built on Qwen-2.5, focused on advancing mathematical reasoning.☆236Updated 2 months ago
- MiroRL is an MCP-first reinforcement learning framework for deep research agent.☆165Updated last month
- End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆305Updated last month
- Extrapolating RLVR to General Domains without Verifiers☆174Updated 2 months ago
- ☆203Updated 6 months ago
- [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆274Updated last month
- [Preprint] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆471Updated this week
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆342Updated last month
- ☆333Updated 2 months ago
- ☆94Updated 9 months ago
- ☆101Updated 4 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆57Updated 10 months ago
- A RLHF Infrastructure for Vision-Language Models☆184Updated 11 months ago
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆115Updated 10 months ago
- Towards a Unified View of Large Language Model Post-Training☆163Updated last month
- [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback☆294Updated last year