Qwen-CUA: Native Computer Use for (Almost) Everything — a screenshot-driven agent that operates computers with keyboard and mouse, jointly developed by the Qwen Team and XLang Lab.

MacAgentBench: Benchmark agents where they actually work — on macOS.

Repository for the implementation of MacArena

让每一次引用都成为可解释的影响力 Turning Every Citation into Explainable Impact

The official repo for the DanQing dataset.

Youtu-VL: Unleashing Visual Potential via Unified Vision-Language Supervision

Scaling Multi-modal Instruction Fine-tuning with Tens of Thousands Vision Task Types

Youtu-Tip: Tap for Intelligence, Keep on Device.

[Neurips 2025 Spotlight] Official repository for the paper: OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts

[CVPR 2025] DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception

A stable & generalizable GRPO method for AR image generation

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

ResNeXt,ResNet, tensorflow,python

An implementation of Covariance Pooling, with the framwork of AlexNet and the dataset of UC Merced

All-day Semantic Segmentation & All-day CityScapes dataset

Use DenseNet40 for remote sensing image scene classification

[CVPR2025] Rethinking Query-based Transformer for Continual Image Segmentation

[ECCV 2024] The official PyTorch implementation of the "Part2Object: Hierarchical Unsupervised 3D Instance Segmentation".

[NeurIPS 2023]DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

[ICCV2023] CoTDet: Affordance Knowledge Prompting for Task Driven Object Detection

The official PyTorch implementation of the CVPR 2023 paper "Contrastive Grouping with Transformer for Referring Image Segmentation".

[ICCV 2025] HQ-CLIP: Leveraging Large Vision-Language Models to Create High-Quality Image-Text Datasets

[ICML 2025] This is the official repository of our paper "What If We Recaption Billions of Web Images with LLaMA-3 ?"

Repository for the BioCLIP 2 model project. [NeurIPS'25 Spotlight] BioCLIP 2 is a biological foundation model trained on TreeOfLife-200M. Despite the narrow training objective, BioCLIP 2 yields ext…

Official Implementation for paper "Unleashing the Power of Visual Foundation Models for Generalizable Semantic Segmentation"

[CVPR 2025 Highlight] SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learning

[CVPR22] Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation