An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.

[CVPR 2026] Official Implementation of Particulate: Feed-Forward 3D Object Articulation

🔭🪐☄️ Reproducible, scriptable stacking pipeline for DWARF 3 smart telescope FITS data with transparent frame selection, registration, and science-grade linear outputs.

🤖🤝 GS-Hub: Empowering mutual intelligence between communities and LLMs for scientific and technological reasoning.

🌱 This repository is devoted to the emergence of Generative Simulation—a concept that hybridizes large language models (LLMs) and simulation. Simulation engines are developed or wrapped in such a way that they can be directly manipulated by generative AI, without requiring intensive retraining or fine-tuning.