视觉大模型 / VLM - arXivDaily 专题

2502.00528 2025-02-04 cs.CV cs.CL 88%

Vision-Language Modeling in PET/CT for Visual Grounding of Positive Findings

Zachary Huemann, Samuel Church, Joshua D. Warner, Daniel Tran, Xin Tie, Alan B McMillan, Junjie Hu, Steve Y. Cho, Meghan Lubner, Tyler J. Bradshaw

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

2412.19406 2024-12-30 cs.CV 88%

MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios

Jiaqi Fan, Jianhua Wu, Jincheng Gao, Jianhao Yu, Yafei Wang, Hongqing Chu, Bingzhao Gao

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

2406.07904 2024-12-10 cs.LG 88%

Grounding Multimodal Large Language Models in Actions

Andrew Szot, Bogdan Mazoure, Harsh Agrawal, Devon Hjelm, Zsolt Kira, Alexander Toshev

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

2402.16050 2024-10-04 cs.CV cs.CL 88%

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge

Yuxuan Wang, Yueqian Wang, Pengfei Wu, Jianxin Liang, Dongyan Zhao, Yang Liu, Zilong Zheng

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

Comments To appear at EMNLP 2024

2403.05346 2024-05-10 cs.CV 88%

VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model

Junsu Kim, Yunhoe Ku, Jihyeon Kim, Junuk Cha, Seungryul Baek

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

Comments Accept to CVPRW2024 (CLvision). The camera-ready version of the manuscript

2311.12327 2024-04-29 cs.CV 88%

Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models

Xiaoyu Yang, Lijian Xu, Hao Sun, Hongsheng Li, Shaoting Zhang

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

Comments 22 pages

2401.06341 2024-04-19 cs.CV cs.RO 88%

AffordanceLLM: Grounding Affordance from Vision Language Models

Shengyi Qian, Weifeng Chen, Min Bai, Xiong Zhou, Zhuowen Tu, Li Erran Li

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

2312.02483 2024-03-07 cs.CV 88%

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model

Guozhang Li, Xinpeng Ding, De Cheng, Jie Li, Nannan Wang, Xinbo Gao

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

2309.04041 2024-01-17 cs.CV cs.CL 88%

Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models

Jiaying Lu, Jinmeng Rao, Kezhen Chen, Xiaoyuan Guo, Yawen Zhang, Baochen Sun, Carl Yang, Jie Yang

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

Comments This paper has been accepted to the AAAI'24 Workshop on Responsible Language Models (ReLM 2024)

2312.02949 2023-12-06 cs.CV 88%

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Hao Zhang, Hongyang Li, Feng Li, Tianhe Ren, Xueyan Zou, Shilong Liu, Shijia Huang, Jianfeng Gao, Lei Zhang, Chunyuan Li, Jianwei Yang

专题命中视觉定位与Grounding ：LLaVA(title,abstract)；grounding(title,abstract)；分类 cs.CV

2608.02470 2026-08-04 cs.CV cs.AI 新提交 88%

Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment

基于专用分割模型实现具身智能视觉语言模型（Agentic VLMs）的细粒度车辆损伤评估

Vishwajeet Shivaji Hogale, Anjali Pai, Nitya Ravi

机构 * Northeastern University（东北大学）

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

AI总结针对VLMs空间定位不可靠问题，本文提出TinyDamage架构，将空间定位委托给专用多任务分割模型，集成至7节点LangGraph智能体流程，在车辆损伤评估中大幅降低报告虚构率。

Comments 8 pages, 2 figures

2606.31148 2026-07-01 cs.CV cs.AI cs.CL 新提交 88%

PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding

PruneGround: 用于3D视觉定位的即插即用空间剪枝框架

Duc Cao Dinh, Khai Le-Duc, Florent Draye, Chris Ngo, Terry Jingchen Zhang, Bernhard Schölkopf, Zhijing Jin

机构 * Knovel Engineering Lab（Knovel工程实验室）； University of Toronto（多伦多大学）； Vector Institute（向量研究所）； ELLIS Institute（ELLIS研究所）； Max Planck Institute（马克斯·普朗克研究所）

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

AI总结提出PruneGround框架，通过语言引导的空间剪枝、多视角描述重构和LLM定位器，在剪枝区域高效定位目标，在多个基准上取得最优结果。

Comments Preprint

2603.14579 2026-07-01 cs.CV cs.LG 版本更新 88%

Medical Image Spatial Grounding with Semantic Sampling

基于语义采样的医学图像空间定位

Andrew Seohwan Yu, Mohsen Hariri, Kunio Nakamura, Mingrui Yang, Xiaojuan Li, Vipin Chaudhary

机构 * Case Western Reserve University（凯斯西储大学）； Cleveland Clinic（克利夫兰诊所）

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

AI总结研究视觉语言模型在医学图像三维空间定位中的挑战，提出MIS-Ground基准和MIS-SemSam优化方法，通过语义采样提升定位精度13.06%。

Comments 10 pages, 2 figures. Accepted at MICCAI 2026

2601.12263 2026-06-09 cs.CL cs.AI cs.LG 版本更新 88%

Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers

多模态生成式引擎优化：针对视觉-语言模型排序器的排名操纵

Yixuan Du, Chenxiao Yu, Haoyan Xu, Ziyi Wang, Yue Zhao, Xiyang Hu

机构 * Georgetown University（乔治城大学）； University of Southern California（南加州大学）； University of Maryland, College Park（马里兰大学学院公园分校）； Arizona State University（亚利桑那州立大学）

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

AI总结提出多模态生成式引擎优化（MGEO）方法，通过联合优化图像扰动和文本后缀，利用视觉-语言模型内部跨模态知识耦合，实现对产品排名的有效操纵，揭示了多模态基础模型知识基础的脆弱性。

Comments Proceedings of the 4th Workshop on Towards Knowledgeable Foundation Models (KnowFM) at ACL 2026

2605.07141 2026-05-11 cs.CV cs.AI 88%

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding

Qwen3-VL-Seg: 解锁基于视觉-语言接地的开放世界指代分割

Yuan Yao, Qiushi Yang, Humen Zhong, Jiangning Wei, Yifang Men, Shuai Bai, Miaomiao Cui, Zhibo Yang

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团）

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

AI总结 Qwen3-VL-Seg通过视觉-语言接地框架实现开放世界指代分割，采用轻量级的框引导掩码解码器，结合多尺度空间特征注入和迭代掩码感知查询优化，实现参数高效且精确的像素级分割。

2602.15872 2026-05-08 cs.RO cs.CV cs.LG 88%

MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

MARVL：通过视觉-语言模型实现机器人操作的多阶段引导

Xunlan Zhou, Xuanlin Chen, Shaowei Zhang, ShengHua Wan, Xiaohai Hu, Lei Yuan, De-chuan Zhan

机构 * School of Intelligent Science and Technology, Nanjing University, China（南京大学智能科学与技术学院）； National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, China（南京大学新型软件技术国家实验室，人工智能学院）； School of Artificial Intelligence, Nanjing University, China（南京大学人工智能学院）； MACS Lab, University of Washington（华盛顿大学MACS实验室）

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

AI总结本文提出MARVL，通过视觉-语言模型实现机器人操作的多阶段引导，解决传统密集奖励函数设计中的问题，提升样本效率和鲁棒性。

2412.08110 2026-05-08 cs.CV cs.CL cs.LG 88%

The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding

构图的艺术：用于组合视觉定位的注意力正则化训练

Jiayun Luo, Mir Rayat Imtiaz Hossain, Pritam Sarkar, Boyang Li, Leonid Sigal

机构 * The University of British Columbia（不列颠哥伦比亚大学）； Nanyang Technological University（南洋理工大学）

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

AI总结本文提出CompART，通过分解标题为以对象为中心的短语并构建复合短语，提升多对象定位能力，验证了其在多种视觉语言模型上的有效性。

2508.00378 2025-10-15 cs.AI cs.CV 88%

CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding

Shixin Yi, Lin Shang

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

Comments The paper is not yet mature and needs further improvement

2509.18405 2025-09-24 cs.CV cs.AI 88%

Check Field Detection Agent (CFD-Agent) using Multimodal Large Language and Vision Language Models

Sourav Halder, Jinjun Tong, Xinyu Wu

机构 * U.S. Bank（美国银行）

专题命中视觉定位与Grounding ：vision language model(title,abstract)；VLM(abstract)；multimodal large language model(abstract)；MLLM(abstract)

Comments 12 pages, 5 figures, 2 tables

2506.15649 2025-06-19 cs.CV cs.LG 88%

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Ankan Deria, Adinath Madhavrao Dukre, Feilong Tang, Sara Atito, Sudipta Roy, Muhammad Awais, Muhammad Haris Khan, Imran Razzak

机构 * Mohamed bin Zayed University of AI（莫扎德人工智能大学）； University of Surrey（萨里大学）； Jio Institute（乔研究所）； UNSW（新南威尔士大学）

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

2411.17237 2026-03-03 cs.CV 88%

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment

Grounding-IQA: 多模态语言模型的接地图像质量评估

Zheng Chen, Xun Zhang, Wenbo Li, Renjing Pei, Fenglong Song, Xiongkuo Min, Xiaohong Liu, Xin Yuan, Yong Guo, Yulun Zhang

机构 * Shanghai Jiao Tong University（上海交通大学）； Joy Future Academy（京东探索研究院）； Huawei Noah’s Ark Lab（华为诺亚实验室）； Westlake University（西湖大学）； Huawei（华为）

专题命中视觉定位与Grounding ：grounding(title,abstract)；visual question answering(abstract)；multimodal large language model(abstract)；MLLM(abstract)

AI总结本文提出grounding-IQA任务范式，通过结合多模态指称与图像质量评估，实现更细粒度的图像质量感知。

Comments Accepted to ICLR 2026. Code is available at: https://github.com/zhengchen1999/Grounding-IQA

2607.21595 2026-07-24 cs.CV cs.AI cs.LG 新提交 88%

3D-Aware VLMs with Implicit and Explicit Geometries

具有隐式和显式几何的3D感知视觉语言模型

Wenhao Li, Xueying Jiang, Quanhao Qian, Deli Zhao, Ran Xu, Shijian Lu, Gongjie Zhang

机构 * Nanyang Technological University（南洋理工大学）； DAMO Academy, Alibaba Group（阿里巴巴达摩院）； HuPan Lab（湖畔实验室）

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

AI总结研究针对多数2D视觉输入的VLM处理3D任务困难的问题，提出VLM-IE3D框架，通过引入隐式和显式几何令牌及3D感知适配器，融合几何表示与视觉线索，在多种3D任务中表现优异。

Comments Accepted by ECCV 2026, Open Sourced

2604.02893 2026-04-06 cs.CV cs.AI cs.LG 88%

Toward an Artificial General Teacher: Procedural Geometry Data Generation and Visual Grounding with Vision-Language Models

迈向人工通用教师：基于视觉-语言模型的程序几何数据生成与视觉语义

Hai Nguyen-Truong, Alper Balbay, Tunga Bayrak

机构 * Freya

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

AI总结本文研究几何教育中的视觉解释问题，提出通过程序生成几何图示数据，结合视觉-语言模型进行领域特定微调，提升几何元素分割性能，并引入几何感知的评估指标。

Comments 12 pages, 7 figures

2311.00047 2023-11-02 cs.AI cs.CL cs.CV cs.LG 88%

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

Yichi Zhang, Jiayi Pan, Yuchen Zhou, Rui Pan, Joyce Chai

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

Comments Accepted at EMNLP 2023 main conference

2608.09789 2026-08-11 cs.CV 新提交 87%

ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

ADOPD：面向多模态大语言模型（MLLM）的工业异常检测的参考特权在线策略蒸馏

Jingtai He, Shiyuan Meng, Wenchao Meng, Qinmin Yang

机构 * Zhejiang University（浙江大学）

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

AI总结本研究针对工业异常检测问题，提出ADOPD参考特权在线策略蒸馏框架，通过参考感知教师监督仅查询的学生模型，在MMAD基准零样本推理下获77.31%平均准确率，优于Qwen3-VL-4B主干及其一样本设置。

2608.07427 2026-08-10 cs.AI cs.PF 新提交 87%

A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy

一图胜千词：视觉语言模型如何在提升准确率的同时降低AI能源成本

Bhavika Jalli, Nikhil Korati Prasanna, Jayanta Choudhury

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

AI总结该研究提出将时间序列编码为二维图的视觉语言模型，可大幅减少输入词元、降低推理能耗，同时在电信异常检测等任务中提升准确率，解决了LLM处理多维度KPI数据的低效问题。

Comments Accepted at the 14th European Conference on Renewable Energy Systems (ECRES), July 7--9, 2026, London, UK

2608.04533 2026-08-06 cs.CV 新提交 87%

EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation

EgoAfford：基于自我中心指称分割的面向任务的可供性定位

Xinyuan Guan, Feifan Chen, Xinyu Zhan, Fu-Cheng Zhang, Cewu Lu, Lixin Yang

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

AI总结针对部件级可供性定位难以适配复杂多步桌面任务的问题，提出基准EgoAfford及参考模型EgoLens，验证了下一步推理与动作角色条件部件定位的互补挑战，为感知与规划联合研究提供基础。

2608.04385 2026-08-06 cs.CV 新提交 87%

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination

ReGround：通过自诊断与视觉重检验恢复多步推理中的视觉接地

Lei Peng, Shuai Lv, Wei Hu

机构 * University of Science and Technology of China（中国科学技术大学）； School of Artificial Intelligence and Data Science（人工智能与数据科学学院）； State Key Laboratory of Precision and Intelligent Chemistry（精准与智能化学国家重点实验室）

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

AI总结 ReGround是无需架构修改或外部工具的两阶段框架，通过自诊断与视觉重检验解决VLMs多步推理中的视觉接地丢失问题，在八个基准上获一致增益且推理开销适度。

Comments Accepted to ACM Multimedia 2026 (MM '26). 8 pages main text, 4 figures, plus appendix

2608.03147 2026-08-06 cs.CV 版本更新 87%

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

CROSS：用于遥感指称分割的级联蒸馏与双约束 grounding

Tingzhang Luo, Ruizhong Liu, Yichao Liu, Cheng Fan, Yu Liu, Jianyuan Guo

专题命中视觉定位与Grounding ：grounding(title,title_cn)；VLM(abstract,abstract_cn)；分类 cs.CV

AI总结针对遥感指称分割中架构弱耦合与语义偏差问题，本文提出CROSS范式，通过LGCD与PSCL实现性能突破，成为RRSIS的稳健新方案。

Comments Accepted at the European Conference on Computer Vision (ECCV) 2026. 20 pages, 6 figures, and 5 tables. Tingzhang Luo and Ruizhong Liu contributed equally. Jianyuan Guo is the corresponding author. Project page: https://clarence-cv.github.io/CROSS/

2608.00877 2026-08-04 cs.LG 新提交 87%

GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMs

GeoArbiter：面向遥感多模态大语言模型的可验证性导向 grounding 方法

Xuechen Li

机构 * University of Minnesota, Twin Cities（明尼苏达大学双城分校）

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

AI总结该研究针对遥感多模态大语言模型的事实断言问题，提出无需训练的 GeoArbiter 流程，通过仅注入图像无法验证的地理事实，有效降低了模型的断言级幻觉并提升了对冲突记录的鲁棒性。

1. 视觉定位与Grounding 7314 篇

Vision-Language Modeling in PET/CT for Visual Grounding of Positive Findings

MLLM-SUL: Multimodal Large Language Model for Semantic Scene Understanding and Localization in Traffic Scenarios

Grounding Multimodal Large Language Models in Actions

Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge

VLM-PL: Advanced Pseudo Labeling Approach for Class Incremental Object Detection via Vision-Language Model

Enhancing Visual Grounding and Generalization: A Multi-Task Cycle Training Approach for Vision-Language Models

AffordanceLLM: Grounding Affordance from Vision Language Models

EtC: Temporal Boundary Expand then Clarify for Weakly Supervised Video Grounding with Multimodal Large Language Model

Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models

LLaVA-Grounding: Grounded Visual Chat with Large Multimodal Models

Grounding Agentic VLMs with Dedicated Segmentation for Fine-Grained Vehicle Damage Assessment

PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding

Medical Image Spatial Grounding with Semantic Sampling

Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers

Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding

MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding

CoRGI: Verified Chain-of-Thought Reasoning with Post-hoc Visual Grounding

Check Field Detection Agent (CFD-Agent) using Multimodal Large Language and Vision Language Models

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Grounding-IQA: Grounding Multimodal Language Model for Image Quality Assessment

3D-Aware VLMs with Implicit and Explicit Geometries

Toward an Artificial General Teacher: Procedural Geometry Data Generation and Visual Grounding with Vision-Language Models

Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?

ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection

A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy

EgoAfford: Task-Oriented Affordance Grounding via Egocentric Referring Segmentation

ReGround: Restoring Visual Grounding in Multi-Step Reasoning through Self-Diagnosis and Visual Re-Examination

CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

GeoArbiter: Verifiability-Guided Grounding for Remote-Sensing Multimodal LLMs