AMAP-ML / GPGLinks
GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning
☆164Updated 4 months ago
Alternatives and similar repositories for GPG
Users that are interested in GPG are comparing it to the libraries listed below
Sorting:
- An Easy-to-use, Scalable and High-performance RLHF Framework designed for Multimodal Models.☆146Updated 5 months ago
- The Next Step Forward in Multimodal LLM Alignment☆181Updated 5 months ago
- Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"☆322Updated 3 weeks ago
- MM-Eureka V0 also called R1-Multimodal-Journey, Latest version is in MM-Eureka☆319Updated 3 months ago
- ✨✨ [ICLR 2025] MME-RealWorld: Could Your Multimodal LLM Challenge High-Resolution Real-World Scenarios that are Difficult for Humans?☆133Updated 7 months ago
- A Self-Training Framework for Vision-Language Reasoning☆86Updated 8 months ago
- The official code of "VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning" [NeurIPS25]☆151Updated 4 months ago
- [NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation☆91Updated 2 weeks 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☆192Updated last week
- ☆72Updated 4 months ago
- The official repository for our paper, "Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning".☆139Updated 3 weeks ago
- Rethinking RL Scaling for Vision Language Models: A Transparent, From-Scratch Framework and Comprehensive Evaluation Scheme☆143Updated 5 months ago
- A RLHF Infrastructure for Vision-Language Models☆184Updated 10 months ago
- SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models☆135Updated 5 months ago
- MME-CoT: Benchmarking Chain-of-Thought in LMMs for Reasoning Quality, Robustness, and Efficiency☆130Updated 2 months ago
- Official repo for "PAPO: Perception-Aware Policy Optimization for Multimodal Reasoning"☆85Updated last month
- OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.☆311Updated 4 months ago
- Official code implementation of Perception R1: Pioneering Perception Policy with Reinforcement Learning☆261Updated 2 months ago
- Pre-trained, Scalable, High-performance Reward Models via Policy Discriminative Learning.☆157Updated last week
- [NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of…☆115Updated 10 months ago
- CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models (NeurIPS 2025)☆152Updated 2 weeks ago
- ☆122Updated 6 months ago
- G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning☆84Updated 4 months ago
- Pixel-Level Reasoning Model trained with RL [NeuIPS25]☆226Updated 3 weeks 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…☆324Updated last month
- [NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning☆71Updated 2 weeks ago
- [CVPR2025 Highlight] Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models☆223Updated 3 months ago
- Latest open-source "Thinking with images" (O3/O4-mini) papers, covering training-free, SFT-based, and RL-enhanced methods for "fine-grain…☆94Updated last month
- [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback☆295Updated last year