Stars
Code Release for "OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data"
Official Code for "SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models"
Official Implementation of "Maximum Likelihood Reinforcement Learning (MaxRL)"
[CVPR 2026 Findings] V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think
JoyAI-Echo: Pushing the Frontier of Long Audio-Visual Generation
Official codes for the paper "GARDO: Reinforcing Diffusion Models without Reward Hacking"
CVPR and NeurIPS poster examples and templates
HY-SOAR:Self-Correction for Optimal Alignment and Refinement in Diffusion Models
Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation
Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence
Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
A unified framework for easy reinforcement learning in Flow-Matching models
E-GRPO: High Entropy Steps Drive Effective Reinforcement Learning for Flow Models
OpenClaw-RL: Train any agent simply by talking
[ICLR 2026] Official implementation of JavisDiT and JavisDiT++ series.
A minimal PyTorch re-implementation of Qwen 3.5
Official Code for "Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic Dynamics"
Official Code for "SoliReward: Mitigating Susceptibility to Reward Hacking and Annotation Noise in Video Generation Reward Models" [CVPR2026]
A curated list of papers on reinforcement learning for video generation
🔥 OneThinker: All-in-one Reasoning Model for Image and Video [CVPR 2026]
Towards Scalable Pre-training of Visual Tokenizers for Generation
Official implementation of HPSv3: Towards Wide-Spectrum Human Preference Score (ICCV2025)
[ICLR2025] Official code implementation of Video-UTR: Unhackable Temporal Rewarding for Scalable Video MLLMs