[CVPR2026] Detect Anything via Next Point Prediction

LabelImg is now part of the Label Studio community. The popular image annotation tool created by Tzutalin is no longer actively being developed, but you can check out Label Studio, the open source …

BoxMOT: Pluggable python and c++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

Efficient vision foundation models for high-resolution generation and perception.

Scenic: A Jax Library for Computer Vision Research and Beyond

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

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

A Diagnostic Guardrail Framework for AI Agent Safety and Security

Notes from How Diffusion Models Work by DeepLearning.ai

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

Benchmarking Knowledge Transfer in Lifelong Robot Learning

Fast and memory-efficient exact attention

Official Code for LightVLA (ICRA 2026)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success

ImageBind One Embedding Space to Bind Them All

[Lumina具身智能社区] 具身智能技术指南 Embodied-AI-Guide

[TLLM'23] PandaGPT: One Model To Instruction-Follow Them All

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

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

LLaVA-VLA: A Simple Yet Powerful Vision-Language-Action Model [ICRA 2026]

Fully Open Framework for Democratized Multimodal Training

Super Rays and Culling Region for Real-Time Updates on Grid-based Occupancy Maps

Example models using DeepSpeed

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

The official GitHub mirror of the Chromium source

Reference PyTorch implementation and models for DINOv3

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈