YOLOE: Real-Time Seeing Anything [ICCV 2025]

Fast Segment Anything

Diagrams for draw.io

This repository represents the official implementation of the paper titled "Towards Generalizable Scene Change Detection (CVPR 2025)".

[ICRA-2025] Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms

Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform

🔥 OneThinker: All-in-one Reasoning Model for Image and Video

DINOv3训练示例

dinov3例子

The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…

Reference PyTorch implementation and models for DINOv3

Reference PyTorch implementation and models for DINOv3

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

Agentic AI Framework for Java Developers

[MathCoder, MathCoder-VL] Family of LLMs/LMMs for mathematical reasoning.

This is the official repository for the paper "MathCanvas: Intrinsic Visual Chain-of-Thought for Multimodal Mathematical Reasoning"

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

Depth Anything 3

A customisable 3D platform for agent-based AI research

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Detect Anything via Next Point Prediction (Based on Qwen2.5-VL-3B)

Fast math typesetting for the web.