Stars
[CVPR 2025] Official implementation of "GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation"
RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding.
Blender addons to make the bridge between Blender and geographic data
A Blender add-on to import models from google maps
BlenderLLM: A LLM specifically designed to generate CAD scripts based on user instructions. These scripts are then executed in Blender to render 3D models.
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation…
An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.
Production-ready platform for agentic workflow development.
🤗 smolagents: a barebones library for agents that think in code.
An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
A very simple framework for state-of-the-art Natural Language Processing (NLP)
Code for the AI Agents blog series—covering agent design, architectures, multi-agent systems, and evaluation.
[CVPR 2024] Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships
The data skeleton from "3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera" http://3dscenegraph.stanford.edu
Open3D: A Modern Library for 3D Data Processing