Implementation of UniJEPA (ICML2026)

Scaling Test-time Training for LLM Reasoning

The long-horizon computer-use harness. Run AI agents across desktop apps and the CLI for extended periods while preserving task state and making reliable progress on complex workflows. Features fre…

🔬 A curated collection of 23,000+ agent skills for empirical research across 8 social science disciplines. | 精选 23,000+ AI Agent 技能库，覆盖8大社会科学学科的实证研究。CoPaper.AI 20分钟完成一篇可复现的规范实证论文，并支持用户上传 Skills。-- …

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

Official implementation of "LidarDM: Generative LiDAR Simulation in a Generated World" (ICRA 2025)

Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.

[NeurIPS 2025] SPIRAL: Semantic-Aware Progressive LiDAR Scene Generation and Understanding

Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)

W8A8/W4A8 inference + optimized SDPA on Apple Silicon — unlocking unused INT8 TensorOps in M5 for 1.2–1.9× faster LLM prefill, plus FlashInfer-inspired GQA decode attention for up to 1.6× SDPA spee…

Skills for Real Engineers. Straight from my .agents directory.

Andrej Karpathy的认知操作系统。不是语录合集，是可运行的思维框架。Made with 女娲.skill

你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.

Production-grade engineering skills for AI coding agents.

[CVPR 2025] SuperPC: A Single Diffusion Model for Point Cloud Completion, Upsampling, Denoising, and Colorization

FlyDSL is the Python front‑end of the project: a Flexible Layout Python DSL for expressing tiling, partitioning, data movement, and kernel structure at a high level.

Claude Code skill for optimizing oversized CLAUDE.md files using progressive disclosure

Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning

Give Claude Code a memory that evolves with your codebase. Hooks automatically capture sessions, the Claude Agent SDK extracts key decisions and lessons, and an LLM compiler organizes everything in…

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

[CVPR 2026 Highlight, the CVPR Compute Gold Star] Offical code for "FastGS: Training 3D Gaussian Splatting in 100 Seconds"

[CVPR 2025] Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes

[ICCV 2025] Detect Anything 3D in the Wild

Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple M4 Mac mini/MacBook — no data leaves your device.Mano-P 是一个开源 GUI-VLA 项目，支持在 Mac mini/M…

[IROS'26] OnFly: Onboard Zero-Shot Aerial Vision-Language Navigation toward Safety and Efficiency

[CVPR 2025] Multiple Object Tracking as ID Prediction