CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

PyTorch code for BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation

Inference Microsoft Florence2 VLM

OpenVLA: An open-source vision-language-action model for robotic manipulation.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

[ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

3D Mapping Library for Autonomous Robots (C++/ROS)

Janus-Series: Unified Multimodal Understanding and Generation Models

ROS 2 Custom Message Visualizer (CMV) is a package that can be used to generate rviz plugins for your custom messages.

A Python script for creating a 3D reconstruction of a scene while simultaneously determining the camera positions relative to that scene (Structure from Motion).

Evaluate Multimodal LLMs as Embodied Agents

Lossy Compression with Pretrained Diffusion Models

Spotify Web AI DJ - client side agentic smarts using Gemma 2, two billion parameter LLM, to play what a user wants via natural speech input

Fully open reproduction of DeepSeek-R1

Rotating FMCW radar simulation based on ray tracing

Multi-Robot Motion Planning with Diffusion Models

Simple Open Source EtherCAT Master

Unitree Go2 simulation platform for testing navigation, decision-making and autonomous tasks. (NVIDIA Isaac/ROS2)

Autobahn WebSocket protocol testsuite

Collection of high-quality robo learning papers for bipedal robots.

agent q - oss advanced reasoning and learning for autonomous ai agents

Flutter + Unreal

LangChain for Go, the easiest way to write LLM-based programs in Go

An open source Plex Media Server Golang SDK

go media services

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

Exploring three.js with python syntax