Starred repositories
[CVPR 2026] ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training
WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
A Claude Code plugin that shows what's happening - context usage, active tools, running agents, and todo progress
Code for "StreamingTalker: Audio-driven 3D Facial Animation with Autoregressive Diffusion Model", AAAI2026 Oral
Monocular whole-body 3D human pose estimation using the SOMA body model
[CVPR 2026] MatAnyone 2: Scaling Video Matting via a Learned Quality Evaluator
An Obsidian plugin that embeds Claude Code as an AI collaborator in your vault
The design language that makes your AI harness better at design.
Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.
A beautiful config generator for Ghostty terminal.
👻 Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.
Elevate your AI research writing, no more tedious polishing ✨
Claude Code VS Code extension patched for Force Local mode — run CLI locally, proxy file ops to remote server via VS Code Remote SSH
Easy and fast 2d human and animal multi pose estimation using SOTA ViTPose [Y. Xu et al., 2022] Real-time performances and multiple skeletons supported.
[CVPR 2025] Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
WiLoR: End-to-end 3D hand localization and reconstruction in-the-wild
Project page for "3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation"
[SIGGRAPH Asia 2025] The official repo for the conference paper "MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis".
🔥(CVPR 2025 Highlight) Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera
Masked Depth Modeling for Spatial Perception
Official implementation of "VideoMaMa: Mask-Guided Video Matting via Generative Prior", CVPR 2026
Official implementation of the paper "Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content".
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.