Stars
Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
GeometryZero: Improving Geometry Solving for LLM with Group Contrastive Policy Optimization
the official code for Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning
[AAAI 2026] ✨ TSPO: Temporal Sampling Policy Optimization for Long-form Video Language Understanding
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
Official codes of "Monet: Reasoning in Latent Visual Space Beyond Image and Language"
【AAAI 2026】GenVidBench: A 6-Million Benchmark for AI-Generated Video Detection
Machine Mental Imagery: Empower Multimodal Reasoning with Latent Visual Tokens (arXiv 2025)
Sparking "Thinking with Videos" via Reinforcement Learning
MiniMax-M2, a model built for Max coding & agentic workflows.
[ICLR 2026] The official repository for paper "ThinkMorph: Emergent Properties in Multimodal Interleaved Chain-of-Thought Reasoning"
This is the official repository for the paper "MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning"
verl: Volcano Engine Reinforcement Learning for LLMs
🔧Tool-Star: Empowering LLM-brained Multi-Tool Reasoner via Reinforcement Learning
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)
Official Repository for "FakingRecipe: Detecting Fake News on Short Video Platforms from the Perspective of Creative Process", ACM MM 2024
Build multi-agent systems that learn and improve with every interaction.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3, Qwen3-MoE, DeepSeek-R1, GLM4.5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, …
[NeurIPS 2025] VideoRFT: Incentivizing Video Reasoning Capability in MLLMs via Reinforced Fine-Tuning
Witness the aha moment of VLM with less than $3.
Links to conference/journal publications in automated fact-checking (resources for the TACL22/EMNLP23 paper).
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
[NeurIPS 2025] MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!
Notes about courses Dive into Deep Learning by Mu Li