Shape and pose estimation via eigenproblem with eigenvector nonlinearities.

ViPE: Video Pose Engine for Geometric 3D Perception

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Let's upgrade cheap off-the-shelf robotic mowers to modern, smart RTK GPS based lawn mowing robots!

🤗 smolagents: a barebones library for agents that think in code.

Artificial Neural Engine Machine Learning Library

Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

A course on aligning smol models.

Run LLMs with MLX

3D Reconstruction for all

Code for our paper "Building Rome with Convex Optimization".

Official repository for LTX-Video

Learning with Multi-Agent Verifier Feedback

A TTS model capable of generating ultra-realistic dialogue in one pass.

Fin-R1 is a large language model for complex financial reasoning developed and open-sourced with the joint efforts of the SUFE-AIFLM-Lab at the School of Statistics and Data Science, Shanghai Unive…

A general and flexible factor graph non-linear least square optimization framework

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.

Fully open reproduction of DeepSeek-R1

Official implementation of MAIA, A Multimodal Automated Interpretability Agent

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

WebRTC API for Unitree GO2 Robots

Python parser for URDFs

DIY split-flap display

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

SAPIEN Manipulation Skill Framework, an open source GPU parallelized robotics simulator and benchmark, led by Hillbot, Inc.