Thibaut CHAUFFIER

ai-job-search. The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

dualdiffusion. Dual Diffusion is a generative diffusion model for music trained on video game soundtracks.

moshi. Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

project-nomad. Project N.O.M.A.D, is a self-contained, offline survival computer packed with critical tools, knowledge, and AI to keep you informed and empowered—anytime, anywhere.

LichtFeld-Studio. Train, inspect, edit, automate, and export 3D Gaussian Splatting scenes from a single native application.

raid. RAID is the largest and most challenging benchmark for AI-generated text detection. (ACL 2024)

Mole. 🐹 Clean, uninstall, analyze, optimize, and monitor your Mac from the terminal.

airllm. Runs 405B LLMs on 8GB VRAM

pruna. Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

DiT. Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

TinyRecursiveModels. Python

MHR. Momentum Human Rig is an anatomically-inspired parametric full-body digital human model developed at Meta. It includes: A parametric body skeletal model; A realistic 3D mesh skinned to the skeleton with levels of detail;A body blendshape and pose corrective model; A facial blendshape model.Its design is friendly for both CG and CV communities.

wgpu. A cross-platform, safe, pure-Rust graphics API.

diffusion-gpt. From baby GPT to diffusion GPT: An annotated implementation of a character-level discrete diffusion model (adapted from Karpathy’s baby GPT).

nanochat. The best ChatGPT that $100 can buy.

fair_groups. Python

PufferLib. Puffing up reinforcement learning

LLMs-from-scratch. Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

MILo. [SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

Hierarchical-Localization. Visual localization made easy with hloc

DoomLedger. Port of DOOM-nano on a Ledger Nanos+

awesome-3D-gaussian-splatting. Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

burn. Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

brush. 3D Reconstruction for all

ollama. Get up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

nerfstudio. A collaboration friendly studio for NeRFs

glomap. [DEPRECATED] GLOMAP - Global Structured-from-Motion Revisited

OpenSplat. Production-grade 3D gaussian splatting with CPU/GPU support for Windows, Mac and Linux 🚀

gsplat. CUDA accelerated rasterization of gaussian splatting

ml-stable-diffusion. Stable Diffusion with Core ML on Apple Silicon

gaussian-splatting. Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

diffusers. 🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

DiffuseVAE. Official implementation of "DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents"

segment-anything. The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.