GAIR-NLP / MAYELinks
Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme
☆147Updated 10 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.☆155Updated last month
- Official code of *Virgo: A Preliminary Exploration on Reproducing o1-like MLLM*☆109Updated 8 months ago
- The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning☆331Updated 8 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆164Updated 4 months ago
- Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning☆193Updated 10 months ago
- MMR1: Enhancing Multimodal Reasoning with Variance-Aware Sampling and Open Resources☆215Updated 4 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…☆392Updated 5 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆172Updated 3 months ago
- "what, how, where, and how well? a survey on test-time scaling in large language models" repository☆86Updated this week
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆182Updated 8 months ago
- [ArXiv] V2PE: Improving Multimodal Long-Context Capability of Vision-Language Models with Variable Visual Position Encoding☆59Updated last year
- [ICLR26]GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning☆173Updated 2 weeks ago
- 🚀ReVisual-R1 is a 7B open-source multimodal language model that follows a three-stage curriculum—cold-start pre-training, multimodal rei…☆196Updated 2 months ago
- Towards a Unified View of Large Language Model Post-Training☆201Updated 5 months ago
- A RLHF Infrastructure for Vision-Language Models☆196Updated last year
- [ICCV 2025 Highlight] The official repository for "2.5 Years in Class: A Multimodal Textbook for Vision-Language Pretraining"☆191Updated 10 months ago
- [COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources☆306Updated 5 months ago
- Extrapolating RLVR to General Domains without Verifiers☆200Updated 6 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆98Updated 8 months ago
- A Self-Training Framework for Vision-Language Reasoning☆88Updated last year
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆123Updated last year
- ☆209Updated 3 months ago
- ☆230Updated last month
- ☆110Updated last year
- [ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.☆532Updated last month
- [AAAI 2026] Official codebase for "GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning".☆95Updated 3 months ago
- A set of examples based on verl for end-to-end RL training recipes.☆166Updated this week
- [ICLR 2026] End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning☆353Updated last month
- [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback☆306Updated last year
- The Next Step Forward in Multimodal LLM Alignment☆197Updated 9 months ago