Stars
Github repository for "Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging" (ICML 2025)
Official repository of 'Visual-RFT: Visual Reinforcement Fine-Tuning' & 'Visual-ARFT: Visual Agentic Reinforcement Fine-Tuning'’
OpenThinkIMG is an end-to-end open-source framework that empowers LVLMs to think with images.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
My learning notes/codes for ML SYS.
Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning
Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey
Reasoning in LLMs: Papers and Resources, including Chain-of-Thought, OpenAI o1, and DeepSeek-R1 🍓
Production-ready platform for agentic workflow development.
A most Frontend Collection and survey of vision-language model papers, and models GitHub repository
yanxiyue / vllm
Forked from vllm-project/vllmA high-throughput and memory-efficient inference and serving engine for LLMs
Understanding R1-Zero-Like Training: A Critical Perspective
R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
Official Repo for Open-Reasoner-Zero
🏝️ OASIS: Open Agent Social Interaction Simulations with One Million Agents.
🦀️ CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents. https://crab.camel-ai.org/
🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
MM-EUREKA: Exploring the Frontiers of Multimodal Reasoning with Rule-based Reinforcement Learning
No fortress, purely open ground. OpenManus is Coming.
A lightweight reproduction of DeepSeek-R1-Zero with indepth analysis of self-reflection behavior.
Explore the Multimodal “Aha Moment” on 2B Model
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
BiomedParse: A Foundation Model for Joint Segmentation, Detection, and Recognition of Biomedical Objects Across Nine Modalities