A feed-forward 3D foundation model for reconstructing scenes from streaming data

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

HY-Embodied: Embodied Foundation Models for Real-World Agents

Unified Codebase for Advanced World Models.

StreamDiffusion, Live Stream APP

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

Compile agent conversations!

[ICLR 2026] UniVideo: Unified Understanding, Generation, and Editing for Videos

Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

One dashboard. An entire research team.

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

小小魔女花园——一款卡牌-自走棋游戏

Official Implementation of SAGE-GRPO:Manifold-Aware Exploration for Reinforcement Learning in Video Generation

[ICLR 2026] Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time

DuckCoding AI工具一键配置 - 支持 Claude Code、CodeX、Gemini CLI 的跨平台桌面应用

OpenSeeker: A search agent with open-source data and models

Seoul World Model: Grounding World Simulation Models in a Real-World Metropolis

[ICLR 2024] Code for FreeNoise based on VideoCrafter

MAGI-1: Autoregressive Video Generation at Scale

Streaming Thinking for VideoLLM Streaming Video Understanding

AGG (AI-Generated Gameverse) is an AI-native game foundation for creation and play. We envision a unified system and a community where researchers, developers, and players evolve together.

InternVL-U is a 4B-parameter unified multimodal model (UMM) that brings multimodal understanding, reasoning, image generation, image editing into a single framework.

Helios: Real Real-Time Long Video Generation Model

Official code for CVPR 2026 paper: VGGT-Det: Mining VGGT Internal Priors for Sensor-Geometry-Free Multi-View Indoor 3D Object Detection