[CVPR 2026 Oral] VGGT Omega

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Advancing Open-source World Models

A real-time system that simultaneously captures human pose, reconstructs the scene in sparse 3D points, and localizes the human in the scene with 6 IMUs and a body-worn phone camera

A real-time motion capture system that estimates poses and global translations using only 6 inertial measurement units

Official Repo for Qwen-RobotNav

A Modular and Multi-Modal Mapping Framework

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

从0开始学习多模态大模型，从概念、架构、训练到部署，系统搭建你的第一套 MLLM 知识体系

The best ChatGPT that $100 can buy.

Coding a Multimodal (Vision) Language Model from scratch in PyTorch with full explanation: https://www.youtube.com/watch?v=vAmKB7iPkWw

Self-supervised learning for spatial perception

Video+code lecture on building nanoGPT from scratch

Real-time AI assistant for Meta Ray-Ban smart glasses -- voice + vision + agentic actions via Gemini Live and OpenClaw

[CVPR 2025] EgoLife: Towards Egocentric Life Assistant

Source code for the ECCV 2022 paper "Benchmarking Localization and Mapping for Augmented Reality".

AirSteady codes

个人主站

空间智能合集

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

open Multi-View Stereo reconstruction library

An open library of computer vision algorithms

[TRO 2025] AirVO upgrades to AirSLAM