verl: Volcano Engine Reinforcement Learning for LLMs

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models

Phantom: Subject-Consistent Video Generation via Cross-Modal Alignment

🌟 Wiki of OI / ICPC for everyone. （某大型游戏线上攻略，内含炫酷算术魔法）

Sora 视频无水印链接提取器

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

[NeurIPS 2025 D&B🔥] OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

A curated list of papers on reinforcement learning for video generation

Kandinsky 5.0: A family of diffusion models for Video & Image generation

Official code for "VideoReward Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning"

(arXiv) MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE

[ICLR 2026] EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling

Contexts Optical Compression

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

Qwen-Image-Lightning: Speed up Qwen-Image model with distillation

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

[ICLR 2026] LongLive: Real-time Interactive Long Video Generation

An official implementation of Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching

HunyuanImage-2.1: An Efficient Diffusion Model for High-Resolution (2K) Text-to-Image Generation​

Pusa: Thousands Timesteps Video Diffusion Model

Official implementation of Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Wan: Open and Advanced Large-Scale Video Generative Models