倪海厦中医课程资料的 Agent Skill：支持课程检索、方证穴位辨析、学习笔记整理与板书截图证据索引。 | An Agent Skill for Ni Haisha TCM course study, formula-pattern lookup, acupoint reference, and screenshot evidence indexing.

INTACT: Isomorphic Intent-to-Action Learning for Search-Free World Models.

Open Frontier Intelligence

🎬ActionMesh: A fast video to animated mesh model with unprecedented quality. Generate animated mesh seamlessly importable into any 3D software in less than a minute.

Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.

Block-Recurrent Dynamics in ViTs 🦖

Homepage

fix some bugs？？

Code for the paper HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement

Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat.

Function-Oriented Abstractions for Procedural 3D Generation in Python

Learning to Simulate Mechanics in World Space

[SIGGRAPH Asia 26 Conditionally Accept]PAct: Part-Decomposed Single-View Articulated Object Generation

The official implementation of “MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction”

EchoStyle: Unlocking High-Fidelity Video Stylization with Reverse Data Synthesis

[NeurIPS 2025] AutoPartGen: Autoregressive 3D Part Generation and Discovery. This is a re-implementation of original model.

Official PyTorch Implementation of "MeshFlow: Mesh Generation with Equivariant Flow Matching" (SIGGRAPH 2026)

DomainShuttle: Freeform Open Domain Subject-driven Text-to-video Generation

Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh R…

[ICLR 26 Oral] Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Official page of ImmerIris: A Large-Scale Dataset and Benchmark for Off-Axis and Unconstrained Iris Recognition in Immersive Applications.

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

Reference code for the articraft paper.

[CVPR 2026 Oral] VGGT Omega

[ICML 2026] PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World

Code of Strips as Tokens: Artist Mesh Generation with Native UV Segmentation. ACM Transactions on Graphics (SIGGRAPH 2026)