A gym environment for xArm

UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning

The memory layer for Personalized AI

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

Neo4j graph construction from unstructured data using LLMs

Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.

a state-of-the-art-level open visual language model | 多模态预训练模型

A Spotify player in the terminal with full feature parity

Implantation of CtrlFormer

LLM101n: Let's build a Storyteller

Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

A collection of full time roles in SWE, Quant, and PM for new grads.

A conda-forge distribution.

[ICCV'21] Learning Spatio-Temporal Transformer for Visual Tracking

[ECCV2022] MOTR: End-to-End Multiple-Object Tracking with TRansformer

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

Assistive Gym, a physics-based simulation framework for physical human-robot interaction and robotic assistance.

Finetune Llama 3, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Train transformer language models with reinforcement learning.

NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This repository contains the open source components of TensorRT.

User-friendly WebUI for LLMs (Formerly Ollama WebUI)

This is a private learning repository for reinforcement learning techniques used in robotics.

In-Hand Object Rotation via Rapid Motor Adaptation (CoRL 2022), and more

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Massively parallel rigidbody physics simulation on accelerator hardware.

A unified framework for robot learning

[IROS'21] SurRoL: An Open-source Reinforcement Learning Centered and dVRK Compatible Platform for Surgical Robot Learning

A very simple news crawler with a funny name