视觉大模型 / VLM

DeltaVLM: Interactive Remote Sensing Image Change Analysis via Instruction-guided Difference Perception

Pei Deng, Wenqian Zhou, Hanlin Wu

机构 * School of Information Science and Technology, Beijing Foreign Studies University（信息科学与技术学院，北京外国语大学） 纠错

专题命中 视觉问答 ：vision-language model(abstract)；visual question answering(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments 12 pages, 5 figures. Submitted to IEEE Transactions on Geoscience and Remote Sensing (TGRS). Code and dataset are available at https://github.com/hanlinwu/DeltaVLM

SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generation

Hao Ye, Mengshi Qi, Zhaohong Liu, Liang Liu, Huadong Ma

机构 * State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（网络与交换技术国家重点实验室，北京邮电大学） 纠错

专题命中 视觉问答 ：vision-language model(abstract)；VLM(abstract)；visual question answering(abstract)；分类 cs.AI

CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making

Songtao Jiang, Yuan Wang, Ruizhe Chen, Yan Zhang, Ruilin Luo, Bohan Lei, Sibo Song, Yang Feng, Jimeng Sun, Jian Wu, Zuozhu Liu

机构 * Zhejiang University（浙江大学） ； Tsinghua University（清华大学） ； Alibaba Group（阿里巴巴集团） ； Angelalign Inc.（Angelalign公司） ； UIUC（伊利诺伊大学香槟分校） 纠错

专题命中 视觉问答 ：vision-language model(abstract)；VLM(abstract)；visual question answering(abstract)；分类 cs.CV

Human-centered Interactive Learning via MLLMs for Text-to-Image Person Re-identification

Yang Qin, Chao Chen, Zhihang Fu, Dezhong Peng, Xi Peng, Peng Hu

机构 * College of Computer Science, Sichuan University（四川大学计算机学院） ； National Key Laboratory of Fundamental Algorithms and Models for Engineering Simulation, Sichuan University（四川大学国家工程仿真基础算法与模型重点实验室） ； Sichuan National Innovation New Vision UHD Video Technology Co., Ltd（四川国家创新新视觉超高清视频技术有限公司） ； Tianfu Jincheng Laboratory（天府锦城实验室） 纠错

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.LG

Worse than Random? An Embarrassingly Simple Probing Evaluation of Large Multimodal Models in Medical VQA

Qianqi Yan, Xuehai He, Xiang Yue, Xin Eric Wang

机构 * University of California, Santa Cruz（加州大学圣克ruz分校） ； Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 视觉问答 ：LLaVA(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.AI

Hallucination at a Glance: Controlled Visual Edits and Fine-Grained Multimodal Learning

Tianyi Bai, Yuxuan Fan, Jiantao Qiu, Fupeng Sun, Jiayi Song, Junlin Han, Zichen Liu, Conghui He, Wentao Zhang, Binhang Yuan

机构 * HKUST（香港科技大学） ； Shanghai AI Lab（上海人工智能实验室） ； Peking University（北京大学） ； HKUST(GZ)（香港科技大学（广州）） ； Oxford University（牛津大学） ； Imperial College London（伦敦帝国理工学院） 纠错

专题命中 视觉问答 ：visual reasoning(abstract)；visual question answering(abstract)；multimodal large language model(abstract)；分类 cs.CV

TextVidBench: A Benchmark for Long Video Scene Text Understanding

Yangyang Zhong, Ji Qi, Yuan Yao, Pengxin Luo, Yunfeng Yan, Donglian Qi, Zhiyuan Liu, Tat-Seng Chua

专题命中 视觉问答 ：visual question answering(abstract)；grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV

Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitation

Weiqi Feng, Yangrui Chen, Shaoyu Wang, Yanghua Peng, Haibin Lin, Minlan Yu

机构 * Harvard University（哈佛大学） ； Bytedance（字节跳动） ； University of Southern California（南加州大学） 纠错

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.AI

A Vision Centric Remote Sensing Benchmark

Abduljaleel Adejumo, Faegheh Yeganli, Clifford Broni-bediako, Aoran Xiao, Naoto Yokoya, Mennatullah Siam

机构 * AMMI/AIMS Senegal（AMMI/AIMS塞内加尔） ； University of British Columbia（不列颠哥伦比亚大学） ； RIKEN AIP（理化学研究所AIP） ； the University of Tokyo（东京大学） 纠错

专题命中 视觉问答 ：visual question answering(abstract)；grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments Eval-FoMo2 Workshop in CVPR 2025

Pixel-SAIL: Single Transformer For Pixel-Grounded Understanding

Tao Zhang, Xiangtai Li, Zilong Huang, Yanwei Li, Weixian Lei, Xueqing Deng, Shihao Chen, Shunping Ji, Jiashi Feng

专题命中 视觉问答 ：vision-language model(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

AstroLLaVA: towards the unification of astronomical data and natural language

Sharaf Zaman, Michael J. Smith, Pranav Khetarpal, Rishabh Chakrabarty, Michele Ginolfi, Marc Huertas-Company, Maja Jabłońska, Sandor Kruk, Matthieu Le Lain, Sergio José Rodríguez Méndez, Dimitrios Tanoglidis

专题命中 视觉问答 ：vision language model(abstract)；LLaVA(abstract)；visual question answering(abstract)；分类 cs.LG

Comments 8 pages, 3 figures, accepted to SCI-FM@ICLR 2025. Code at https://w3id.org/UniverseTBD/AstroLLaVA

FaceBench: A Multi-View Multi-Level Facial Attribute VQA Dataset for Benchmarking Face Perception MLLMs

Xiaoqin Wang, Xusen Ma, Xianxu Hou, Meidan Ding, Yudong Li, Junliang Chen, Wenting Chen, Xiaoyang Peng, Linlin Shen

专题命中 视觉问答 ：LLaVA(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments Accepted by CVPR2025

Seeing and Reasoning with Confidence: Supercharging Multimodal LLMs with an Uncertainty-Aware Agentic Framework

Zhuo Zhi, Chen Feng, Adam Daneshmend, Mine Orlu, Andreas Demosthenous, Lu Yin, Da Li, Ziquan Liu, Miguel R. D. Rodrigues

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.AI

A Benchmark for Crime Surveillance Video Analysis with Large Models

Haoran Chen, Dong Yi, Moyan Cao, Chensen Huang, Guibo Zhu, Jinqiao Wang

专题命中 视觉问答 ：LLaVA(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

FINECAPTION: Compositional Image Captioning Focusing on Wherever You Want at Any Granularity

Hang Hua, Qing Liu, Lingzhi Zhang, Jing Shi, Zhifei Zhang, Yilin Wang, Jianming Zhang, Jiebo Luo

专题命中 视觉问答 ：vision-language model(abstract)；VLM(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Preprint

VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding

Xiang Li, Jian Ding, Mohamed Elhoseiny

专题命中 视觉问答 ：vision-language model(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

Comments Accepted for publication at NeruIPS 2024 Dataset and Benchmark Track

ZALM3: Zero-Shot Enhancement of Vision-Language Alignment via In-Context Information in Multi-Turn Multimodal Medical Dialogue

Zhangpu Li, Changhong Zou, Suxue Ma, Zhicheng Yang, Chen Du, Youbao Tang, Zhenjie Cao, Ning Zhang, Jui-Hsin Lai, Ruei-Sung Lin, Yuan Ni, Xingzhi Sun, Jing Xiao, Jieke Hou, Kai Zhang, Mei Han

专题命中 视觉问答 ：vision-language model(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

DesignQA: A Multimodal Benchmark for Evaluating Large Language Models' Understanding of Engineering Documentation

Anna C. Doris, Daniele Grandi, Ryan Tomich, Md Ferdous Alam, Mohammadmehdi Ataei, Hyunmin Cheong, Faez Ahmed

专题命中 视觉问答 ：LLaVA(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.AI

CVLUE: A New Benchmark Dataset for Chinese Vision-Language Understanding Evaluation

Yuxuan Wang, Yijun Liu, Fei Yu, Chen Huang, Kexin Li, Zhiguo Wan, Wanxiang Che

专题命中 视觉问答 ：vision-language model(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers

Dachuan Shi, Chaofan Tao, Anyi Rao, Zhendong Yang, Chun Yuan, Jiaqi Wang

专题命中 视觉问答 ：vision-language model(abstract)；visual reasoning(abstract)；visual question answering(abstract)；分类 cs.CV

Comments ICML 2024. Code: https://github.com/sdc17/CrossGET

HOI-Ref: Hand-Object Interaction Referral in Egocentric Vision

Siddhant Bansal, Michael Wray, Dima Damen

专题命中 视觉问答 ：vision language model(abstract)；VLM(abstract)；visual question answering(abstract)；分类 cs.CV

Comments Project Page: https://sid2697.github.io/hoi-ref/

Visual Hallucination: Definition, Quantification, and Prescriptive Remediations

Anku Rani, Vipula Rawte, Harshad Sharma, Neeraj Anand, Krishnav Rajbangshi, Amit Sheth, Amitava Das

专题命中 视觉问答 ：vision-language model(abstract)；VLM(abstract)；visual question answering(abstract)；分类 cs.AI

InfMLLM: A Unified Framework for Visual-Language Tasks

Qiang Zhou, Zhibin Wang, Wei Chu, Yinghui Xu, Hao Li, Yuan Qi

专题命中 视觉问答 ：visual question answering(abstract)；grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV

Comments 8

What Large Language Models Bring to Text-rich VQA?

Xuejing Liu, Wei Tang, Xinzhe Ni, Jinghui Lu, Rui Zhao, Zechao Li, Fei Tan

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Lightweight In-Context Tuning for Multimodal Unified Models

Yixin Chen, Shuai Zhang, Boran Han, Jiaya Jia

专题命中 视觉问答 ：LLaVA(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

Comments Preprint

What Makes for Good Visual Tokenizers for Large Language Models?

Guangzhi Wang, Yixiao Ge, Xiaohan Ding, Mohan Kankanhalli, Ying Shan

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Comments 15 pages, 3 figures. Project released at: https://github.com/TencentARC/GVT

Language Is Not All You Need: Aligning Perception with Language Models

Shaohan Huang, Li Dong, Wenhui Wang, Yaru Hao, Saksham Singhal, Shuming Ma, Tengchao Lv, Lei Cui, Owais Khan Mohammed, Barun Patra, Qiang Liu, Kriti Aggarwal, Zewen Chi, Johan Bjorck, Vishrav Chaudhary, Subhojit Som, Xia Song, Furu Wei

专题命中 视觉问答 ：visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV

Answer Questions with Right Image Regions: A Visual Attention Regularization Approach

Yibing Liu, Yangyang Guo, Jianhua Yin, Xuemeng Song, Weifeng Liu, Liqiang Nie

专题命中 视觉问答 ：visual reasoning(abstract)；visual question answering(abstract)；grounding(abstract)；分类 cs.CV

Comments ACM TOMM 2021

What Does a Temporal Benchmark Score Measure? Decomposing Channel Use in Video VLM Evaluation

时间基准分数衡量的是什么？分解视频视觉语言模型评估中的通道使用情况

Farrukh Rahman

机构 * Microsoft（微软） ； Georgia Institute of Technology（佐治亚理工学院） 纠错

专题命中 视觉问答 ：VLM(title)；分类 cs.CV、cs.LG

AI总结 研究视频视觉语言模型评估中时间基准分数衡量问题，提出无标签筛选方法“反转下降”区分模型通道使用情况，如Molmo2和Qwen3-VL，指出综合分数不能反映潜在失败模式，此区分在多基准和任务中成立。

Comments 9 pages, 11 pages supplemental

Location-Aware Pretraining for Medical Difference Visual Question Answering

面向位置的预训练方法用于医学差异视觉问答

Denis Musinguzi, Caren Han, Prasenjit Mitra

机构 * Department of Electrical and Computer Engineering, Carnegie Mellon University, Kigali, Rwanda（电气与计算机工程系，卡内基梅隆大学，刚果（金）基利齐） ； University of Melbourne, Melbourne, Australia（墨尔本大学，墨尔本，澳大利亚） 纠错

专题命中 视觉问答 ：visual question answering(title)；分类 cs.CV、cs.AI

AI总结 本文提出一种面向位置的预训练框架，结合AREF、GCAP和CAREF任务，提升医学差异VQA中细粒度空间视觉表征能力，实现胸部X光图像中临床相关变化的准确识别与推理。

Comments 11 pages