‍Official Repository of CVPR2026 Paper: ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions

Evaluating AI Agents on Continuous Software Evolution

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

VocoType 是一款运行在本地端侧的隐私安全语音输入工具，通过快捷键即可将语音实时转换为文字并自动输入到当前应用。支持语音转文字MCP、AI 优化文本、自定义替换词典、录音视频转文字等功能，让语音输入更高效、更安全。

Web-based task scheduling and machine resource management tool, designed for Deep Learning and bare-metal GPU server nodes. 基于 Web 的任务调度与计算资源管理工具，专为深度学习和GPU裸机集群设计。

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Academic Research Skills for Claude Code: research → write → review → revise → finalize

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 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

[CVPR 2026] V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties

Assignment skeleton for course on Discrete Differential Geometry (15-458/858)

Kilo is the all-in-one agentic engineering platform. Build, ship, and iterate faster with the most popular open source coding agent. #1 coding agent on OpenRouter. 1.5M+ Kilo Coders. 25T+ tokens pr…

✨ Self hosted, always-on AI agent platform run in containers. Create multiple bots with long memory, and connect them to Telegram, Discord, Feishu(Lark), Matrix, etc (like OpenClaw).

Awesome AI Memory | LLM Memory | A curated knowledge base on AI memory for LLMs and agents, covering long-term memory, reasoning, retrieval, and memory-native system design. Awesome-AI-Memory 是一个 集…

Official repository of "BIGS: Bimanual Category-agnostic Interaction Reconstruction from Monocular Videos via 3D Gaussian Splatting" (CVPR, 2025)

Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and shaping the future!

Native and Compact Structured Latents for 3D Generation

DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data

PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)

Real-Time 6D Pose Tracker in High-Dynamic Scenes

Easily export the Genshin Impact wish record.

Hunyuan 3D Part Segmentation and Generation Pipeline

[CVPR2025] EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild

Dexbotic: Open-Source Vision-Language-Action Toolbox

Tencent Cloud API 3.0 SDK for Python

We create D3D-HOI a dataset of monocular videos with ground truth annotations of 3D object pose and part motion during human-object interaction.