多模态大模型

A Fourier-enhanced multi-modal 3D small object optical mark recognition and positioning method for percutaneous abdominal puncture surgical navigation

Zezhao Guo, Yanzhong Guo, Zhanfang Zhao

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.AI

Comments 19 pages, 6 figures,

PARIS3D: Reasoning-based 3D Part Segmentation Using Large Multimodal Model

Amrin Kareem, Jean Lahoud, Hisham Cholakkal

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.AI

Comments 14 pages

AI Powered Road Network Prediction with Multi-Modal Data

Necip Enes Gengec, Ergin Tari, Ulas Bagci

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.AI

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

Siobhan Mackenzie Hall, Fernanda Gonçalves Abrantes, Hanwen Zhu, Grace Sodunke, Aleksandar Shtedritski, Hannah Rose Kirk

专题命中 多模态评测 ：image-text(title)；分类 cs.CV、cs.CL

Comments NeurIPS Datasets and Benchmarks 2023. Data and code available at https://github.com/oxai/visogender

Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models

Sumit Pandey, Kuan-Fu Chen, Erik B. Dam

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.AI

Multimodal Recommender Systems in the Prediction of Disease Comorbidity

Aashish Cheruvu

专题命中 多模态评测 ：multimodal(title)；分类 cs.CL、cs.AI

Comments 2022 Fourth International Conference on Transdisciplinary AI (TransAI)

Journal ref Fourth International Conference on Transdisciplinary AI (TransAI), Laguna Hills, CA, USA, 2022, pp. 79-82

Weakly Supervised Multi-Modal 3D Human Body Pose Estimation for Autonomous Driving

Peter Bauer, Arij Bouazizi, Ulrich Kressel, Fabian B. Flohr

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.AI

Comments 7 pages, Accepted at IEEE-IV 2023

Visual Question Answering in Remote Sensing with Cross-Attention and Multimodal Information Bottleneck

Jayesh Songara, Shivam Pande, Shabnam Choudhury, Biplab Banerjee, Rajbabu Velmurugan

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Sample Efficient Multimodal Semantic Augmentation for Incremental Summarization

Sumanta Bhattacharyya, Ramesh Manuvinakurike, Sahisnu Mazumder, Saurav Sahay

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Multi-modal Protein Knowledge Graph Construction and Applications

Siyuan Cheng, Xiaozhuan Liang, Zhen Bi, Huajun Chen, Ningyu Zhang

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CL、cs.AI

Comments Accepted by AAAI 2023 (Student Abstract). Dataset available in https://zjunlp.github.io/project/ProteinKG65/

Crossmodal-3600: A Massively Multilingual Multimodal Evaluation Dataset

Ashish V. Thapliyal, Jordi Pont-Tuset, Xi Chen, Radu Soricut

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Comments EMNLP 2022

Towards Multimodal Multitask Scene Understanding Models for Indoor Mobile Agents

Yao-Hung Hubert Tsai, Hanlin Goh, Ali Farhadi, Jian Zhang

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.AI

Comments Submitted to ICRA2023

ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding

Bingning Wang, Feiyang Lv, Ting Yao, Yiming Yuan, Jin Ma, Yu Luo, Haijin Liang

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.CL

Comments CIKM2022 camera ready version

A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning

Gerald Schwiebert, Cornelius Weber, Leyuan Qu, Henrique Siqueira, Stefan Wermter

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Comments Accepted to LREC 2022

Journal ref Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 6829-6836

Multimodal Attention Networks for Low-Level Vision-and-Language Navigation

Federico Landi, Lorenzo Baraldi, Marcella Cornia, Massimiliano Corsini, Rita Cucchiara

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Comments Computer Vision and Image Understanding (CVIU)

Multi-modal Identification of State-Sponsored Propaganda on Social Media

Xiaobo Guo, Soroush Vosoughi

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CL、cs.AI

Comments Proceedings of the 25th International Conference on Pattern Recognition (ICPR 2020)

Estimating Presentation Competence using Multimodal Nonverbal Behavioral Cues

Ömer Sümer, Cigdem Beyan, Fabian Ruth, Olaf Kramer, Ulrich Trautwein, Enkelejda Kasneci

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.MM

Multi-Threshold Attention U-Net (MTAU) based Model for Multimodal Brain Tumor Segmentation in MRI scans

Navchetan Awasthi, Rohit Pardasani, Swati Gupta

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.AI

Multi-Modal Depth Estimation Using Convolutional Neural Networks

Sadique Adnan Siddiqui, Axel Vierling, Karsten Berns

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.AI

Comments submitted to IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)

Vyaktitv: A Multimodal Peer-to-Peer Hindi Conversations based Dataset for Personality Assessment

Shahid Nawaz Khan, Maitree Leekha, Jainendra Shukla, Rajiv Ratn Shah

专题命中 多模态评测 ：multimodal(title)；分类 cs.AI、cs.MM

Team Neuro at SemEval-2020 Task 8: Multi-Modal Fine Grain Emotion Classification of Memes using Multitask Learning

Sourya Dipta Das, Soumil Mandal

专题命中 多模态评测 ：multi-modal(title)；分类 cs.CV、cs.CL

Comments Proceedings of the International Workshop on Semantic Evaluation (SemEval)

Faithful Multimodal Explanation for Visual Question Answering

Jialin Wu, Raymond J. Mooney

专题命中 多模态评测 ：multimodal(title)；分类 cs.CV、cs.CL

Comments In ACL 2019 BlackboxNLP workshop

A Joint Model for Multimodal Document Quality Assessment

Aili Shen, Bahar Salehi, Timothy Baldwin, Jianzhong Qi

专题命中 多模态评测 ：multimodal(title)；分类 cs.CL、cs.AI

OmniPath: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility

OmniPath: 用于审计轮椅可达性的多模态智能体框架

ASM Mobarak Hossain, Nadim Mahmud, Vaskar Raychoudhury, Md Osman Gani

机构 * Causal AI Lab, Department of Information Systems, University of Maryland Baltimore County（因果AI实验室，信息系统系，马里兰大学巴尔的摩分校） ； Department of Computer Science & Software Engineering, Miami University（计算机科学与软件工程系，迈阿密大学） 纠错

专题命中 多模态评测 ：multi-modal(title,comments)；分类 cs.AI

AI总结 提出OmniPath框架，融合OSM网络拓扑与机载LiDAR数据，通过虚拟遍历量化坡度、横坡等物理摩擦点，按ADA标准分级评估轮椅可达性，经实地验证有效识别标准地图遗漏的障碍。

Comments 10 pages, 13 figures. Submitted to IEEE COMPSAC 2026. OmniPath: A Multi-Modal Agentic Framework for Auditing Wheelchair Accessibility

M3T: A New Benchmark Dataset for Multi-Modal Document-Level Machine Translation

Benjamin Hsu, Xiaoyu Liu, Huayang Li, Yoshinari Fujinuma, Maria Nadejde, Xing Niu, Yair Kittenplon, Ron Litman, Raghavendra Pappagari

专题命中 多模态评测 ：multi-modal(title,comments)；分类 cs.CL

Comments NAACL 2024, dataset at https://github.com/amazon-science/m3t-multi-modal-translation-bench

Mitigating GenAI-Powered Evidence Pollution for Out-Of-Context Misinformation Detection

缓解生成式人工智能（GenAI）驱动的证据污染以检测脱离上下文的虚假信息

Zehong Yan, Peng Qi, Wynne Hsu, Mong Li Lee

专题命中 多模态评测 ：multimodal(abstract)；cross-modal(abstract)；分类 cs.CV、cs.CL、cs.MM

AI总结 该研究针对GenAI污染证据削弱OOC多模态虚假信息检测的问题，提出跨模态证据重排序与声明-证据推理策略，在基准数据集上验证了其对现有检测器鲁棒性的提升效果。

Comments 15 pages, 11 figures

MCBench: A Multicontext Safety Assessment Benchmark for Omni Large Language Models

MCBench：面向全能大语言模型的多上下文安全评估基准

Manh Luong, Tamas Abraham, Junae Kim, Amar Kaur, Rollin Omari, Gholamreza Haffari, Trang Vu, Lizhen Qu, Dinh Phung

机构 * Monash University（墨尔本大学） ； Defence Science and Technology Group（国防科学与技术集团） 纠错

专题命中 多模态评测 ：multimodal(abstract)；cross-modal(abstract)；分类 cs.CL、cs.AI、eess.AS

AI总结 针对现有多模态安全基准仅处理视觉输入的局限，提出MCBench基准，包含1196个跨四类安全场景的测试，要求整合多模态信息进行安全评估，揭示当前全能大语言模型在跨模态安全推理上的不足。

LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning

LongChart VQA：面向具备复杂多图表推理能力的多模态大语言模型的综合基准

Ziyan Xiao, Yinghao Zhu, Wenting Zhang, Heaju Kim, Lequan Yu

机构 * The University of Hong Kong（香港大学） 纠错

专题命中 多模态评测 ：multimodal(abstract)；MLLM(abstract)；分类 cs.CV、cs.CL、cs.AI

AI总结 LongChart VQA是面向具备复杂多图表推理能力的MLLMs的综合基准，该基准含平均6.5张图像与31.2个问题，评估10个SOTA MLLMs发现其准确率随计算复杂性提升下降，为多图表推理研究指明方向。

Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents

从失败中学习：计算机使用代理的推理时自我改进

Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy, Yuhui Zhang

机构 * Stanford University（斯坦福大学） ； Tsinghua University（清华大学） 纠错

专题命中 多模态评测 ：multimodal(abstract)；MLLM(abstract_cn)；分类 cs.CV、cs.CL、cs.AI

AI总结 提出失败驱动的自我改进循环，利用LLM诊断失败模式并生成代码补丁，在OSWorld基准上将OpenCUA-72B模型成功率从42.3%提升至48.9%，无需额外训练成本。

Comments Published in ECCV 2026

When Prompts Mislead: Textual Dominance and Diagnostic Bias in MLLMs

当提示误导：多模态大语言模型中的文本主导与诊断偏差

Inhyuk Park, Doohyun Park

专题命中 多模态评测 ：MLLM(abstract,abstract_cn)；multimodal(abstract)

AI总结 研究揭示在医学多模态大语言模型中，文本提示会主导视觉线索，导致诊断偏差，即使模型具备空间定位能力，提示策略仍可能不安全。

Comments Accepted to the CVPR 2026 MMFM-BIOMED Workshop