Highlights
- Pro
Lists (15)
Stars
Official repository for LegoGPT, the first approach for generating physically stable LEGO brick models from text prompts.
Seed1.5-VL, a vision-language foundation model designed to advance general-purpose multimodal understanding and reasoning, achieving state-of-the-art performance on 38 out of 60 public benchmarks.
[Arxiv Paper 2504.09130]: VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
8000 Unleashing Vecset Diffusion Model for Fast Shape Generation within 1 Second.
A video translation and dubbing tool powered by LLMs, offering professional-grade translations and one-click full-process deployment. It can generate content optimized for platforms like YouTubeοΌTβ¦
Image editing is worth a single LoRA! 0.1% training data for fantastic image editing! Training released! Surpasses GPT-4o in ID persistence! Official ComfyUI workflow release! Only 4GB VRAM is enouβ¦
A Modular Toolkit for Robot Kinematic Optimization
A final sanity checklist to help your CS paper get accepted, not desk rejected.
GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
π Geometric Computer Vision Library for Spatial AI
CUDA Python: Performance meets Productivity
A SOTA open-source image editing model, which aims to provide comparable performance against the closed-source models like GPT-4o and Gemini 2 Flash.
(π§ WIP) a course of LLM inference serving on Apple Silicon for systems engineers.
XLeRobot: Practical Household Dual-Arm Mobile Robot for ~$660
(CVPR2025 Highlight) Official repository of paper "Panorama Generation From NFoV Image Done Right"
MAGI-1: Autoregressive Video Generation at Scale
π WorldGen - Generate Any 3D Scene in Seconds
An extremely fast Python package and project manager, written in Rust.
Python implementation of convertion between equirectangular, cubemap and perspective. (equirect2cube, cube2equirect, equirect2perspec)
Lightweight coding agent that runs in your terminal
[CoRL2024] Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation
Repo for Objaverse++, Curated 3D Object Dataset with Quality Annotations
Pusa: Thousands Timesteps Video Diffusion Model
[ARXIV'25] ReCamMaster: Camera-Controlled Generative Rendering from A Single Video
[ICLR 2025] GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering