Highlights
- Pro
Lists (8)
Stars
Flash Attention implementatio with attention score
[CVPR2026]RAGTrack: Language-aware RGBT Tracking with Retrieval-Augmented Generation
R1-Track: Direct Application of MLLMs to Visual Object Tracking via Reinforcement Learning.
Official code of paper "GEMeX: A Large-Scale, Groundable, and Explainable Medical VQA Benchmark for Chest X-ray Diagnosis" [ICCV 2025]
BARE: Towards Bias-Aware and Reasoning-Enhanced One-Tower Visual Grounding
VPTracker: Global Vision-Language Tracking via Visual Prompt and MLLM
A multi-platform proxy client based on ClashMeta,simple and easy to use, open-source and ad-free.
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...)…
[nature biomedical engineering 2025] Official code for paper: A generalist foundation model and database for open-world medical image segmentation (MedSegX)
Vision-Language based Visual Object Tracking
MLLMSeg: Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder
[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型
Progressive Language-guided Visual Learning for Multi-Task Visual Grounding
[ICME 2025] Overcoming Feature Contamination by Unidirectional Information Modeling for Vision-Language Tracking
[ICME 2025] A Simple and Better Baseline for Visual Grounding
[NeurIPS2025 Spotlight 🔥 ] Official implementation of 🛸 "UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface"
[NeurIPS2024] - SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
[TPAMI 2025] Towards Visual Grounding: A Survey
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The official pytorch implementation of our AAAI 2024 paper "Unifying Visual and Vision-Language Tracking via Contrastive Learning"
Script for download the dataset 'ChestX-ray8'
[ECCV 2024] Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance