Scalable toolkit for efficient model reinforcement

Multimodal RL training framework for diffusion & omni models

https://avocado-captioner.github.io/

[ICML 2026] Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions

[ICLR 2026] An official implementation of "CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning"

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training

FuseAI Project

Codebase for Merging Language Models (ICML 2024)

Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning

🔥 OneThinker: All-in-one Reasoning Model for Image and Video [CVPR 2026]

[CVPR 2026] Official repo for "VideoSSR: Video Self-Supervised Reinforcement Learning"

[CVPR 2026] Boosting Reasoning in Large Multimodal Models via Activation Replay

Official code for "Rethinking Chain-of-Thought Reasoning for Videos"

[CVPR2026] VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

[CVPRF 2026] Official PyTorch code of "Weaver: End-to-End Agentic System Training for Video Interleaved Reasoning".

Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

[ICLR2026] VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

RoboBrain 2.5: Advanced version of RoboBrain. Depth in Sight, Time in Mind. 🎉🎉🎉

Spirit-v1.5: A Robotic Foundation Model by Spirit AI

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing

Building General-Purpose Robots Based on Embodied Foundation Model

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning