Stars
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a querya…
A vector index built on TurboQuant, written in Rust with Python bindings
Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.
Code Repository for MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos (ECCV 2024)
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.
[ICLR 2026] Towards Unified Latent VLA for Whole-body Loco-manipulation Control
Official dataset and code for "ELMO: Enhanced Real-time LiDAR Motion Capture through Upsampling" and "MOVIN: Real-time Motion Capture using a Single LiDAR"
On the detection of synthetic images generated by diffusion models
[ICLR 2023] Masked Frequency Modeling for Self-Supervised Visual Pre-Training
[CVPR2025] Any-Resolution AI-Generated Image Detection by Spectral Learning
[CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".
Beyond Artifacts: Real-Centric Envelope Modeling (REM) for reliable AI-generated image detection. Includes the RealChain benchmark featuring emerging generators and chain degradations for realistic…
📝The official repository of "Rethinking Cross-Generator Image Forgery Detection through DINOv3"
Academic Research Skills for Claude Code: research → write → review → revise → finalize
Official report of the paper "TrueFake: A Real World Case Dataset of Last Generation Fake Images also Shared on Social Networks"
Reference PyTorch implementation and models for DINOv3
This repository is the official implementation of NeurIPS 2025 Paper "Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable".
A curated collection of the latest research and resources on AI-Generated Image and Video Detection.
Official repository for CVPR 2025 paper: OpenSDI: Spotting Diffusion-Generated Images in the Open World
TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…
An offline-first scientific writing workspace powered by Claude. LaTeX + Python + 100+ scientific skills all running locally.
Official implementation of Kimodo, a kinematic motion diffusion model for high-quality human(oid) motion generation.
DNA-RENDERING: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering
RigAnything: Template‑Free Autoregressive Rigging for Diverse 3D Assets (SIGGRAPH TOG 2025)