Stars
Implementation of Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players
[SIGGRAPH 2026] Pixal3D: Pixel-Aligned 3D Generation from Images
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video
Official code, models, and data for Vista4D: Video Reshooting with 4D Point Clouds (CVPR 2026 Highlight)
HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds
The agent that grows with you
Information collection for the Happy Horse AI video generator model. Official demo and updates at happyhorses.io.
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/
"AI-Trader: 100% Fully-Automated Agent-Native Trading"
"OpenSpace: Make Your Agents: Smarter, Low-Cost, Self-Evolving" -- Community: https://open-space.cloud/
AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced as audio narration, and the option to follow your own .pptx template, not slide images …
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale
[CVPR 2026 Highlight & Best Paper of VideoWorldModel Workshop] NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Official Implementation of Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training
[CVPR'26 Highlight] SimRecon: SimReady Compositional Scene Reconstruction from Real Videos
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
[CVPR '26] SceneTok: A Compressed, Diffusable Token Space for 3D Scenes
A community collection of OpenClaw use cases for making life easier.
Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interact with the model while enjoying updates from Anthropic.
[CVPR 2026 Highlight] tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction
Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.