视觉大模型 / VLM

MPerS: Dynamic MLLM MixExperts Perception-Guided Remote Sensing Scene Segmentation

MPerS: 动态多模态大语言模型混合专家感知引导的遥感场景分割

Ziyi Wang, Xianping Ma, Ziyao Wang, Hongyang Zhang, Man On Pun

机构 * The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）） ； Southwest Jiaotong University（西南交通大学） 纠错

专题命中 视觉定位与Grounding ：MLLM(title,abstract)；LLaVA(abstract,abstract_cn)；分类 cs.CV、cs.AI

AI总结 本文提出MPerS方法，通过设计多提示生成高质量遥感描述，结合DINOv3提取视觉特征，利用动态混合专家模块和语言查询引导注意力实现精准分割。

Comments Accepted to CVPR 2026 Findings. 11 pages, 6 figures

Decoding by Perturbation: Mitigating MLLM Hallucinations via Dynamic Textual Perturbation

解码中的扰动：通过动态文本扰动缓解多模态大语言模型的幻觉

Sihang Jia, Shuliang Liu, Songbo Yang, Yibo Yan, Xin Zou, Xuming Hu

机构 * The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州）） 纠错

专题命中 视觉定位与Grounding ：MLLM(title)；grounding(abstract,abstract_cn)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

AI总结 本文提出Decoding by Perturbation方法，通过动态文本扰动缓解多模态大语言模型的幻觉问题，通过控制文本干预减少语言先验的影响，提升解码稳定性。

VGS-Decoding: Visual Grounding Score Guided Decoding for Hallucination Mitigation in Medical VLMs

VGS-Decoding：基于视觉 grounding 分数的解码方法用于医疗 VLM 中的幻觉抑制

Govinda Kolli, Adinath Madhavrao Dukre, Behzad Bozorgtabar, Dwarikanath Mahapatra, Imran Razzak

机构 * MBZUAI ； Rajiv Gandhi University of Knowledge Technologies（拉贾·甘地知识技术大学） ； Aarhus University（奥胡斯大学） ； Khalifa University（卡里玛大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；LLaVA(abstract)；分类 cs.CV、cs.LG

AI总结 本文提出 VGS-Decoding 方法，通过视觉 grounding 分数指导解码以减少医疗 VLM 的幻觉问题，实验表明在多个数据集上取得了显著提升，且仅引入2倍推理开销。

AgriChat: A Multimodal Large Language Model for Agriculture Image Understanding

AgriChat：一种用于农业图像理解的多模态大语言模型

Abderrahmene Boudiaf, Irfan Hussain, Sajid Javed

机构 * Department of Computer Science, Khalifa University of Science and Technology（卡利法科技大学计算机科学系） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

AI总结 本文提出AgriChat，一种基于多模态大语言模型的农业图像理解系统，通过整合视觉描述与网络增强的科学检索，生成农业基准数据集，提升农业领域的模型鲁棒性和可信度。

LoV3D: Grounding Cognitive Prognosis Reasoning in Longitudinal 3D Brain MRI via Regional Volume Assessments

LoV3D：通过区域体积评估在纵向3D脑MRI中实现认知预后推理

Zhaoyang Jiang, Zhizhong Fu, David McAllister, Yunsoo Kim, Honghan Wu

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

AI总结 LoV3D通过纵向3D脑MRI的区域体积评估，实现认知预后推理，其核心方法是结合3D视觉-语言模型，通过区域解剖评估、纵向对比和诊断输出，提高诊断准确性与泛化能力。

See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent

看见、行动、适应：通过个性化VLM引导代理的主动感知用于无监督跨域视觉适应

Tianci Tang, Tielong Cai, Hongwei Wang, Gaoang Wang

机构 * Zhejiang University, Hangzhou, China（浙江大学） 纠错

专题命中 视觉定位与Grounding ：VLM(title,abstract)；vision-language model(abstract)；grounding(abstract)；分类 cs.CV、cs.AI

AI总结 Sea$^2$通过智能姿态控制代理实现无监督跨域视觉适应，利用现成感知模型提升视觉任务性能。

MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision

MedReasoner: 通过强化学习实现从临床思维到像素级精度的推理 grounding

Zhonghao Yan, Muxi Diao, Yuxuan Yang, Ruoyan Jing, Jiayuan Xu, Kaizhou Zhang, Lele Yang, Yanxi Liu, Kongming Liang, Zhanyu Ma

专题命中 视觉定位与Grounding ：grounding(title,abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

AI总结 MedReasoner 通过强化学习实现从临床推理到像素级精度的医学影像 grounding，提出统一医学推理 grounding 任务和 U-MRG-14K 数据集，展示其在医学影像分析中的优越性能。

Comments AAAI2026

CrashChat: A Multimodal Large Language Model for Multitask Traffic Crash Video Analysis

CrashChat: 一种多模态大语言模型用于多任务交通事故视频分析

Kaidi Liang, Ke Li, Xianbiao Hu, Ruwen Qin

机构 * Stony Brook University（石溪大学） ； The Pennsylvania State University（宾夕法尼亚州立大学） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

AI总结 CrashChat是一种多模态大语言模型，用于多任务交通事故视频分析，通过任务解耦和分组策略提升事故识别、定位等任务的性能。

Enhancing Radiology Report Generation and Visual Grounding using Reinforcement Learning

通过强化学习增强放射学报告生成和视觉基础识别

Benjamin Gundersen, Nicolas Deperrois, Samuel Ruiperez-Campillo, Thomas M. Sutter, Julia E. Vogt, Michael Moor, Farhad Nooralahzadeh, Michael Krauthammer

机构 * University of Zurich（苏黎世大学） ； ETH Zurich（苏黎世联邦理工学院） ； Zurich University of Applied Sciences（苏黎世应用科学大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

AI总结 本研究通过强化学习和思考机制提升放射学报告生成和视觉基础识别的性能，展示了在医学VLMs中RL作为SFT的有效补充。

Comments 10 pages main text (3 figures, 3 tables), 31 pages in total

Chain-of-Ground: Improving GUI Grounding via Iterative Reasoning and Reference Feedback

Chain-of-Ground: 通过迭代推理和参考反馈提升GUI定位

Aiden Yiliu Li, Bizhi Yu, Daoan Lei, Tianhe Ren, Shilong Liu

机构 * University College London（伦敦大学学院） ； Chico Future AI Lab（芝加哥未来人工智能实验室） ； The University of Hong Kong（香港大学） ； Princeton University（普林斯顿大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；visual reasoning(abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

AI总结 Chain-of-Ground通过迭代推理和参考反馈提升GUI定位，实现68.4的准确率，并在现实世界界面中表现优异。

Suppressing VLM Hallucinations with Spectral Representation Filtering

Ameen Ali, Tamim Zoabi, Lior Wolf

机构 * Tel Aviv University（特拉维夫大学） 纠错

专题命中 视觉定位与Grounding ：VLM(title)；vision-language model(abstract)；LLaVA(abstract)；grounding(abstract)

edgeVLM: Cloud-edge Collaborative Real-time VLM based on Context Transfer

Chen Qian, Xinran Yu, Zewen Huang, Danyang Li, Qiang Ma, Fan Dang, Xuan Ding, Guangyong Shang, Zheng Yang

机构 * Tsinghua University（清华大学） ； Beijing Jiaotong University（北京交通大学） ； Inspur Yunzhou Industrial Internet Co., Ltd（Inspur云洲工业互联网有限公司） 纠错

专题命中 视觉定位与Grounding ：VLM(title,abstract)；vision-language model(abstract)；grounding(abstract)；分类 cs.CV、cs.AI

RSVG-ZeroOV: Exploring a Training-Free Framework for Zero-Shot Open-Vocabulary Visual Grounding in Remote Sensing Images

Ke Li, Di Wang, Ting Wang, Fuyu Dong, Yiming Zhang, Luyao Zhang, Xiangyu Wang, Shaofeng Li, Quan Wang

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments This work is accepted by AAAI 2026

LLM-RG: Referential Grounding in Outdoor Scenarios using Large Language Models

Pranav Saxena, Avigyan Bhattacharya, Ji Zhang, Wenshan Wang

机构 * Birla Institute of Technology and Science Pilani, K.K Birla Goa Campus（比拉理工学院和科学学院，K.K Birla Goa校区） ； Carnegie Mellon University, Robotics Institute（卡内基梅隆大学，机器人研究所） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；VLM(abstract)；分类 cs.CV、cs.AI

Comments Human-aware Embodied AI Workshop @ IROS 2025

InfraGPT Smart Infrastructure: An End-to-End VLM-Based Framework for Detecting and Managing Urban Defects

Ibrahim Sheikh Mohamed, Abdullah Yahya Abdullah Omaisan

机构 * Independent Researchers（独立研究者） 纠错

专题命中 视觉定位与Grounding ：VLM(title,abstract)；vision language model(abstract)；LLaVA(abstract)；分类 cs.CV、cs.AI

Self-Consistency as a Free Lunch: Reducing Hallucinations in Vision-Language Models via Self-Reflection

Mingfei Han, Haihong Hao, Jinxing Zhou, Zhihui Li, Yuhui Zheng, Xueqing Deng, Linjie Yang, Xiaojun Chang

机构 * Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence（计算机视觉系，Mohamed Bin Zayed人工智能大学） ； School of Information Science and Technology, University of Science and Technology of China（信息科学与技术学院，中国科学技术大学） ； Bytedance Seed（字节跳动种子） ； School of Computer Science, Qinghai Normal University（计算机科学学院，青海师范大学） 纠错

专题命中 视觉定位与Grounding ：vision-language model(title,abstract)；LLaVA(abstract)；grounding(abstract)；分类 cs.CV、cs.AI

SparkUI-Parser: Enhancing GUI Perception with Robust Grounding and Parsing

Hongyi Jing, Jiafu Chen, Chen Rao, Ziqiang Dang, Jiajie Teng, Tianyi Chu, Juncheng Mo, Shuo Fang, Huaizhong Lin, Rui Lv, Chenguang Ma, Lei Zhao

专题命中 视觉定位与Grounding ：grounding(title,abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

TruthLens: Visual Grounding for Universal DeepFake Reasoning

Rohit Kundu, Shan Jia, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury

专题命中 视觉定位与Grounding ：grounding(title,abstract)；multimodal large language model(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding

Zhuoran Yu, Yong Jae Lee

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；LLaVA(abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments Accepted by COLM 2025

A Training-Free, Task-Agnostic Framework for Enhancing MLLM Performance on High-Resolution Images

Jaeseong Lee, Yeeun Choi, Heechan Choi, Hanjung Kim, Seonjoo Kim

机构 * Yonsei University（延世大学） 纠错

专题命中 视觉定位与Grounding ：MLLM(title,abstract)；grounding(abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments Accepted at CVPR 2025 Workshop on Emergent Visual Abilities and Limits of Foundation Models

Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning

Tzu-Chun Chien, Chieh-Kai Lin, Shiang-Feng Tsai, Ruei-Chi Lai, Hung-Jen Chen, Min Sun

机构 * National Tsing Hua University (NTHU)（国立清华大学） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；LLaVA(abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

When language and vision meet road safety: leveraging multimodal large language models for video-based traffic accident analysis

Ruixuan Zhang, Beichen Wang, Juexiao Zhang, Zilin Bian, Chen Feng, Kaan Ozbay

机构 * New York University（纽约大学） 纠错

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su

机构 * The Ohio State University（俄亥俄州立大学） ； Orby AI（Orby人工智能） 纠错

专题命中 视觉定位与Grounding ：grounding(title,abstract)；LLaVA(abstract)；multimodal large language model(abstract)；分类 cs.CV、cs.AI

Comments Accepted to ICLR 2025 (Oral). Project Homepage: https://osu-nlp-group.github.io/UGround/

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Woody Haosheng Gan, Deqing Fu, Julian Asilis, Ollie Liu, Dani Yogatama, Vatsal Sharan, Robin Jia, Willie Neiswanger

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.LG

The Evolving Landscape of LLM- and VLM-Integrated Reinforcement Learning

Sheila Schoepp, Masoud Jafaripour, Yingyue Cao, Tianpei Yang, Fatemeh Abdollahi, Shadan Golestan, Zahin Sufiyan, Osmar R. Zaiane, Matthew E. Taylor

专题命中 视觉定位与Grounding ：VLM(title,abstract)；vision-language model(abstract)；grounding(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 4 figures

Exploring Spatial Language Grounding Through Referring Expressions

Akshar Tumu, Parisa Kordjamshidi

专题命中 视觉定位与Grounding ：grounding(title,abstract)；vision-language model(abstract)；visual question answering(abstract)；分类 cs.CV、cs.AI

Vision Language Models are In-Context Value Learners

Yecheng Jason Ma, Joey Hejna, Ayzaan Wahid, Chuyuan Fu, Dhruv Shah, Jacky Liang, Zhuo Xu, Sean Kirmani, Peng Xu, Danny Driess, Ted Xiao, Jonathan Tompson, Osbert Bastani, Dinesh Jayaraman, Wenhao Yu, Tingnan Zhang, Dorsa Sadigh, Fei Xia

专题命中 视觉定位与Grounding ：vision language model(title)；vision-language model(abstract)；VLM(abstract)；grounding(abstract)

Comments Project website and demo: https://generative-value-learning.github.io/

Advancing Object Detection in Transportation with Multimodal Large Language Models (MLLMs): A Comprehensive Review and Empirical Testing

Huthaifa I. Ashqar, Ahmed Jaber, Taqwa I. Alhadidi, Mohammed Elhenawy

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；visual reasoning(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Visual Prompting in Multimodal Large Language Models: A Survey

Junda Wu, Zhehao Zhang, Yu Xia, Xintong Li, Zhaoyang Xia, Aaron Chang, Tong Yu, Sungchul Kim, Ryan A. Rossi, Ruiyi Zhang, Subrata Mitra, Dimitris N. Metaxas, Lina Yao, Jingbo Shang, Julian McAuley

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.LG

Comments 10 pages

Genixer: Empowering Multimodal Large Language Models as a Powerful Data Generator

Henry Hengyuan Zhao, Pan Zhou, Mike Zheng Shou

专题命中 视觉定位与Grounding ：multimodal large language model(title,abstract)；grounding(abstract)；MLLM(abstract)；分类 cs.CV、cs.AI

Comments Accepted by ECCV 2024