多模态大模型

AttAnchor: Guiding Cross-Modal Token Alignment in VLMs with Attention Anchors

Junyang Zhang, Tianyi Zhu, Thierry Tambe

机构 * California Institute of Technology（加州理工学院） ； Stanford University（斯坦福大学） 纠错

专题命中 多模态训练与对齐 ：cross-modal(title,abstract)；分类 cs.CV、cs.AI

Comments 31 pages, 17 figures

Multi-Modal Sentiment Analysis with Dynamic Attention Fusion

Sadia Abdulhalim, Muaz Albaghdadi, Moshiur Farazi

机构 * University of Doha for Science and Technology（多哈科学技术大学） 纠错

专题命中 多模态训练与对齐 ：multi-modal(title)；multimodal(abstract)；分类 cs.CL、cs.AI

Comments Paper accepted for presentation at the ACS/IEEE 22nd International Conference on Computer Systems and Applications (AICCSA 2025)

GateMABSA: Aspect-Image Gated Fusion for Multimodal Aspect-based Sentiment Analysis

Adamu Lawan, Haruna Yunusa

专题命中 多模态训练与对齐 ：multimodal(title,abstract)；分类 cs.CL

Comments 6 pages, 2 tables

MSD-KMamba: Bidirectional Spatial-Aware Multi-Modal 3D Brain Segmentation via Multi-scale Self-Distilled Fusion Strategy

Dayu Tan, Ziwei Zhang, Yansan Su, Xin Peng, Yike Dai, Chunhou Zheng, Weimin Zhong

机构 * Key Laboratory of Intelligent Computing and Signal Processing, Ministry of Education, Anhui University（智能计算与信号处理重点实验室，教育部，安徽大学） ； Key Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology（能源化工过程智能制造重点实验室，教育部，东华大学） 纠错

专题命中 多模态训练与对齐 ：multi-modal(title,abstract)；分类 cs.CV

WildFusion: Multimodal Implicit 3D Reconstructions in the Wild

Yanbaihui Liu, Boyuan Chen

机构 * Duke University（杜克大学） 纠错

专题命中 多模态训练与对齐 ：multimodal(title,abstract)；分类 cs.MM

Comments Our project website is at: http://generalroboticslab.com/WildFusion

Journal ref 2025 IEEE International Conference on Robotics and Automation (ICRA)

Semantic Compression via Multimodal Representation Learning

Eleonora Grassucci, Giordano Cicchetti, Aurelio Uncini, Danilo Comminiello

机构 * Dept. of Information Engineering, Electronics, and Telecomm.（信息工程、电子与电信系） 纠错

专题命中 多模态训练与对齐 ：multimodal(title,abstract)

LatXGen: Towards Radiation-Free and Accurate Quantitative Analysis of Sagittal Spinal Alignment Via Cross-Modal Radiographic View Synthesis

Moxin Zhao, Nan Meng, Jason Pui Yin Cheung, Chris Yuk Kwan Tang, Chenxi Yu, Wenting Zhong, Pengyu Lu, Chang Shi, Yipeng Zhuang, Teng Zhang

机构 * Department of Orthopaedics and Traumatology, The University of Hong Kong（香港大学骨科与创伤学系） ； Department of Joint Surgery, Shandong Provincial Hospital Affiliated to Shandong First Medical University（山东省第一医科大学附属山东省人民医院骨科） 纠错

专题命中 多模态训练与对齐 ：cross-modal(title)；分类 cs.CV、cs.AI

Comments 8 pages, 6 figures

S$^3$F-Net: A Multi-Modal Approach to Medical Image Classification via Spatial-Spectral Summarizer Fusion Network

Md. Saiful Bari Siddiqui, Mohammed Imamul Hassan Bhuiyan

机构 * Department of Computer Science and Engineering, BRAC University（计算机科学与工程系，布拉克大学） ； Department of Electrical and Electronic Engineering, Bangladesh University of Engineering and Technology（电气与电子工程系，孟加拉国工程与技术大学） 纠错

专题命中 多模态训练与对齐 ：multi-modal(title)；分类 cs.CV、cs.AI

Comments Submitted to IEEE Journal of Biomedical and Health Informatics (JBHI). This preprint includes few additional details not present in the journal submission

Patient-specific Biomolecular Instruction Tuning

Irsyad Adam, Zekai Chen, David Laub, Shaun Porwal, Arda Pekis, Kevin Brown

机构 * Standard Model Biomedicine（标准模型生物医学） ； University of California, San Diego（加州大学圣地亚哥分校） 纠错

专题命中 多模态训练与对齐 ：multimodal(abstract)；multi-modal(abstract)；分类 cs.CL、cs.AI

FuseCodec: Semantic-Contextual Fusion and Supervision for Neural Codecs

Md Mubtasim Ahasan, Rafat Hasan Khan, Tasnim Mohiuddin, Aman Chadha, Tariq Iqbal, M Ashraful Amin, Amin Ahsan Ali, Md Mofijul Islam, A K M Mahbubur Rahman

机构 * Center for Computational & Data Sciences, Independent University, Bangladesh（计算与数据科学中心，独立大学，孟加拉国） ； Amazon GenAI（亚马逊生成人工智能） ； Qatar Computing Research Institute（卡塔尔计算研究所） ； University of Virginia（弗吉尼亚大学） 纠错

专题命中 多模态训练与对齐 ：cross-modal(abstract)；分类 cs.CL、cs.AI、eess.AS

Guided Manifold Alignment with Geometry-Regularized Twin Autoencoders

Jake S. Rhodes, Adam G. Rustad, Marshall S. Nielsen, Morgan Chase McClellan, Dallan Gardner, Dawson Hedges

机构 * Department of Statistics（统计学系） ； Department of Computer Science（计算机科学系） ； Neuroscience Center（神经科学中心） ； Neuroscience Center and Department of Psychology（神经科学中心和心理学系） ； Department of Psychology（心理学系） 纠错

专题命中 多模态训练与对齐 ：multi-modal(abstract)；cross-modal(abstract)

Comments 10 pages, 4 figures, 7 tables. Accepted at the MMAI workshop at ICDM, 2025

ThermalGen: Style-Disentangled Flow-Based Generative Models for RGB-to-Thermal Image Translation

Jiuhong Xiao, Roshan Nayak, Ning Zhang, Daniel Tortei, Giuseppe Loianno

机构 * New York University（纽约大学） ； Technology Innovation Institute（技术创新研究所） ； University of California, Berkeley（加州大学伯克利分校） 纠错

专题命中 多模态训练与对齐 ：multi-modal(abstract)；分类 cs.CV

Comments 23 pages including the checklist and appendix. Accepted at NeurIPS 2025

ThanoRA: Task Heterogeneity-Aware Multi-Task Low-Rank Adaptation

Jian Liang, Wenke Huang, Xianda Guo, Guancheng Wan, Bo Du, Mang Ye

机构 * Wuhan University（武汉大学） ； ByteDance（字节跳动） ； National University of Defense Technology（国防科技大学） ； Nanyang Technological University（南洋理工大学） ； The AGH University of Krakow（克拉科夫AGH大学） 纠错

专题命中 多模态训练与对齐 ：multimodal(abstract)；分类 cs.AI

A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning

Yaya Zhao, Kaiqi Zhao, Zixuan Tang, Zhiyuan Liu, Xiaoling Lu, Yalei Du

机构 * Center for Applied Statistics, School of Statistics, Innovation Platform, Renmin University of China（应用统计中心、统计学院、创新平台、中国人民大学） ； Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳学院） 纠错

专题命中 多模态训练与对齐 ：multimodal(abstract)；分类 cs.CV

From Static to Dynamic: a Survey of Topology-Aware Perception in Autonomous Driving

Yixiao Chen, Ruining Yang, Xin Chen, Jia He, Dongliang Xu, Yue Yao

机构 * Sems ； Shandong University（山东大学） 纠错

专题命中 多模态训练与对齐 ：multimodal(abstract)；分类 cs.CV

Comments 13 pages, 3 figures

SynDoc: A Hybrid Discriminative-Generative Framework for Enhancing Synthetic Domain-Adaptive Document Key Information Extraction

Yihao Ding, Soyeon Caren Han, Yanbei Jiang, Yan Li, Zechuan Li, Yifan Peng

机构 * The University of Western Australia（西澳大学） ； The University of Melbourne（墨尔本大学） ； The University of Sydney（悉尼大学） ； Weill Cornell Medicine, Cornell University（韦尔·科恩医学中心，康奈尔大学） 纠错

专题命中 多模态训练与对齐 ：multimodal(abstract)；分类 cs.CV

Comments Work in progress

RServe: Overlapping Encoding and Prefill for Efficient LMM Inference

Tianyu Guo, Tianming Xu, Xianjie Chen, Junru Chen, Nong Xiao, Xianwei Zhang

专题命中 多模态训练与对齐 ：multimodal(abstract)

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction

Marzieh Ajirak, Oded Bein, Ellen Rose Bowen, Dora Kanellopoulos, Avital Falk, Faith M. Gunning, Nili Solomonov, Logan Grosenick

机构 * Department of Psychiatry, Weill Cornell Medicine（威立·科恩医学部） ； Feil Family Brain & Mind Research Institute, Weill Cornell Medicine（费尔家族脑与心灵研究研究所） 纠错

专题命中 其他多模态 ：multimodal(title,abstract)；分类 cs.AI

Robust Multi-Modal Face Anti-Spoofing with Domain Adaptation: Tackling Missing Modalities, Noisy Pseudo-Labels, and Model Degradation

Ming-Tsung Hsu, Fang-Yu Hsu, Yi-Ting Lin, Kai-Heng Chien, Jun-Ren Chen, Cheng-Hsiang Su, Yi-Chen Ou, Chiou-Ting Hsu, Pei-Kai Huang

机构 * College of Computer and Cyber Security, Fujian Normal University（计算机与网络安全部，福建师范大学） ； Department of Computer Science, National Tsing Hua University（计算机科学系，国立清华大学） 纠错

专题命中 其他多模态 ：multi-modal(title,abstract)；分类 cs.CV

Optimal thresholds and algorithms for a model of multi-modal learning in high dimensions

Christian Keup, Lenka Zdeborová

机构 * Statistical Physics of Computation Laboratory（计算物理实验室） 纠错

专题命中 其他多模态 ：multi-modal(title,abstract)

Journal ref J. Stat. Mech. (2025) 093302

Uncertainty-Guided Expert-AI Collaboration for Efficient Soil Horizon Annotation

Teodor Chiaburu, Vipin Singh, Frank Haußer, Felix Bießmann

机构 * Einstein Center Digital Future Berlin Germany ； Einstein Center Digital Future 纠错

专题命中 其他多模态 ：multimodal(abstract)；分类 cs.AI

Comments 11 pages, 7 figures, presented at ECAI 2025, CLEAR-AI Workshop, Bologna

Ancestry Tree Clustering for Particle Filter Diversity Maintenance

Ilari Vallivaara, Bingnan Duan, Yinhuan Dong, Tughrul Arslan

机构 * Visiting Research Fellow University of Edinburgh Edinburgh, UK（访问研究员 爱丁堡大学 英国爱丁堡） ； School of Engineering University of Edinburgh Edinburgh, UK（工程学院 爱丁堡大学 英国爱丁堡） 纠错

专题命中 其他多模态 ：multimodal(abstract)；分类 cs.AI

Comments 15th International Conference on Indoor Positioning and Indoor Navigation, 15-18 September 2025, Tampere, Finland Originally 8 pages. The online version with appendices is 14 pages