Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

PyTorch code and models for VJEPA2 self-supervised learning from video.

TruckDrive: Long-Range Autonomous Highway Driving Dataset

Fast disk usage analyzer with console interface written in Go

[CVPR 2025] Multiple Object Tracking as ID Prediction

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

AI agents running research on single-GPU nanochat training automatically

[CVPR 2026 Findings] ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers

A collection of useful functions for 3D vision & graphics research in Python.

Official code for "LagerNVS Latent Geometry for Fully Neural Real-time Novel View Synthesis" (CVPR 2026)

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[CVPR 2025] Prompt Depth Anything

A Simple Baseline for BEV Perception

[ICLR 2026 Oral] Latent Particle World Models official repository

Browser-based 3D perception explorer for Waymo, nuScenes, and Argoverse 2

Visually Consistent Hierarchical Image Classification (H-CAST), ICLR, 2025

Official code for BEVDepth.

An official code release of our CVPR'23 paper, BEVHeight

C++/Python Sparse Volumetric TSDF Fusion

A LiDAR odometry pipeline that just works

Real-time 2.5D elevation mapping engine for embedded mobile robots: C++17 core with optional ROS1/ROS2 support

Masked Depth Modeling for Spatial Perception

A library for differentiable robotics on manifolds.

[CVPR 2026] Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching

Elevation Mapping on GPU.

NumPy & SciPy for GPU

Accepted to ECCV 2026

Coursera Open Courses from University of Toronto