Karpathy's LLM-Wiki vision, fully realized — wiki-centric full-lifecycle AI research platform powered by Claude Code

BEDLAM (CVPR 2023) render pipeline tools

Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plans that survive context loss and /clear, plus a deterministic completion gate and multi-a…

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

[CVPR 2026]Official implementation of "UniTEX: Universal High Fidelity Generative Texturing for 3D Shapes"

TAPIP3D: Tracking Any Point in Persistent 3D Geometry

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

SAM 3D Objects with Multi-view Images

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

Public repository for Agent Skills

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

[ICLR 2026] An unified model for 4D human-scene reconstruction

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Inverse Dynamics Trajectory Optimization for Contact-Implicit Model Predictive Control

Various retargeting optimizers to translate human hand motion to robot hand motion.

A general physic-based retargeting framework.

A general physic-based retargeting framework.

beyondAMP provides a unified pipeline to integrate Adversarial Motion Priors (AMP) into any IsaacLab robot setup, with minimal modifications and full compatibility with custom robot designs.

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

SAM 3D Objects

[CVPR 2025] InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

Vision package for robot manipulation and learning research

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Official Implementation of paper "St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World"

[NeurIPS 2024] Official implementation of InterControl