Stars
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
A library for soundscape synthesis and augmentation
Official Codebase for our CVPR 2026 paper UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching
Unified automatic quality assessment for speech, music, and sound.
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Official PyTorch implementation of the paper "TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis" ICCV 2023
HY-Motion model for 3D human motion or 3D character animation generation.
[CVPR 2026] CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
Machine Learning and Computer Vision Engineer - Technical Interview Questions
Official implementation for "Generating Diverse and Natural 3D Human Motions from Texts (CVPR2022)."
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
VIP cheatsheets for Stanford's CS 229 Machine Learning
[ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
COLMAP - Structure-from-Motion and Multi-View Stereo
[ICCV 2025 Oral] RePoseD: Efficient Relative Pose Estimation With Known Depth Information
Release repo for our SLAM Handbook
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
A lightweight suite of motion imitation methods for training controllers.
An unified model for 4D human-scene reconstruction
A collection of full time roles in SWE, Quant, and PM for new grads.
2025 & 2026 New grad full-time roles in SWE, Quant, and PM.