Stars
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Official Repository of "Unpaired Image-to-Image Translation via Neural Schrödinger Bridge" (ICLR 2024)
[ECCV 2024] Official implementation of "Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization"
Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
(TPAMI 2025) Invertible Diffusion Models for Compressed Sensing [PyTorch]
Best Papers of Top Venues like CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, ...
LBM: Latent Bridge Matching for Fast Image-to-Image Translation ✨ (ICCV 2025 Highlight)
Collection of awesome resources on image-to-image translation.
🦄 🎃 👻 V2Ray 路由规则文件加强版，可代替 V2Ray 官方 geoip.dat 和 geosite.dat，适用于 V2Ray、Xray-core、mihomo(Clash-Meta)、hysteria、Trojan-Go 和 leaf。Enhanced edition of V2Ray rules dat files, applicable to V2Ray, Xray-core…
An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.
[NeurIPS 2025] DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response
HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation (2026)
Download the Kimi-K2.6 Lightweight Installer — is not just a code editor, it is an autonomous software factory on your desktop. We have integrated the latest Kimi 2.6 model from Moonshot AI with th…
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
The official implementation for RiO-DETR: DETR for Real-time Oriented Object Detection
[AAAI 2026]"Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection"
Personalize Segment Anything Model (SAM) with 1 shot in 10 seconds
The official implementation of Conditional Diffusion for SAR to Optical Image Translation
Effortless data labeling with AI support from Segment Anything and other awesome models.
[BMVC 2025] Official Implementation of the paper "PerSense: Personalized Instance Segmentation in Dense Images"
Video-MME-v2: Towards the Next Stage in Benchmarks for Comprehensive Video Understanding
HY-Embodied: Embodied Foundation Models for Real-World Agents
SteerViT is a framework that equips any ViT with the ability to steer both its global and local visual representations with natural language.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.