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…

Lightweight coding agent that runs in your terminal

official code for "Large Language Models as Optimizers"

Build Conversational AI in minutes ⚡️

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Guide for fine-tuning Llama/Mistral/CodeLlama models and more

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

🦜🔗 The platform for reliable agents.

Open-source search and retrieval database for AI applications.

Mastering Diverse Domains through World Models

Code for the PoseScript (ECCV 22) and PoseFix (ICCV 23) papers.

Head tracking software for MS Windows, Linux, and Apple OSX

Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System

Stable Diffusion built-in to Blender

Python client library for Modal

pack and unpack binary data.

A latent text-to-image diffusion model

A minimalist remake of the classic game Tetris using SDL2, now with AI.

[CVPR-2022 (oral)]-Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

Plenoxels: Radiance Fields without Neural Networks

Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

Front End repo for the Nowcasting project.

Code release for our paper, "SimNet: Enabling Robust Unknown Object Manipulation from Pure Synthetic Data via Stereo"

Cloudy is a friendly Discord bot, designed to help out the hacker. He can do various things, including realistic chat and code generation.

A Robust and Versatile Monocular Visual-Inertial State Estimator

Official implementation of "Implicit Neural Representations with Periodic Activation Functions"

Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research

Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO