Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory

Offical repo for the paper "LATO.2: Factorized 3D Mesh Generation with Vertex and Topology Flow"

The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

Sutskever 30 implementations inspired by https://papercode.vercel.app/ | For Agents, use https://github.com/pageman/Sutskever-Agent | Polyglot / Multi-Backed version at https://github.com/pageman/s…

Official Repo For PerceptionDLM Codebase

The open-source CapCut alternative

[ECCV 2026] Official code for paper "Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO"

Vision as Unified Multimodal Generation

金谷园饺子馆.Skill - 北邮旁的饺子馆

The Source Code for OmniVideoBench @ICLR 2026

[ECCV 2026] Official code for paper: MotionAtlas: Detailed Region Captioning for Motion-Centric Videos

Flexible and Pluggable Serving Engine for Diffusion LLMs

Qwen-AgentWorld: Language World Models for General Agents

🚀 Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Apache Parquet Format

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

📚 A curated list of Awesome Efficient dLLMs Papers with Codes

Collect some World Models for Autonomous Driving (and Robotic, etc.) papers.

A framework for few-shot evaluation of language models.

Use agent to learn agent - A skeleton course on how to design, build, and operate production AI agents

DreamX-World: A General-Purpose Interactive World Model

[ICML 2026] The official implementation of paper "Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification"

Bernini is a unified framework for video generation and editing that combines an MLLM-based semantic planner with a DiT-based renderer.