多模态大模型

Robust Fusion Controller: Degradation-aware Image Fusion with Fine-grained Language Instructions

Hao Zhang, Yanping Zha, Qingwei Zhuang, Zhenfeng Shao, Jiayi Ma

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

When Less Is More: A Sparse Facial Motion Structure For Listening Motion Learning

Tri Tung Nguyen Nguyen, Quang Tien Dam, Dinh Tuan Tran, Joo-Ho Lee

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

Gaze-Guided Learning: Avoiding Shortcut Bias in Visual Classification

Jiahang Li, Shibo Xue, Yong Su

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

Comments 10 pages, 5 figures, 3 tables, URL: https://szyyjl.github.io/eye_tracking_data.github.io/

MIMRS: A Survey on Masked Image Modeling in Remote Sensing

Shabnam Choudhury, Akhil Vasim, Michael Schmitt, Biplab Banerjee

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

Comments 6 pages

Multi-lingual Multi-turn Automated Red Teaming for LLMs

Abhishek Singhania, Christophe Dupuy, Shivam Mangale, Amani Namboori

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

Comments Accepted at TrustNLP@NAACL 2025

X-Capture: An Open-Source Portable Device for Multi-Sensory Learning

Samuel Clarke, Suzannah Wistreich, Yanjie Ze, Jiajun Wu

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

Comments Project page: https://xcapture.github.io/

DALIP: Distribution Alignment-based Language-Image Pre-Training for Domain-Specific Data

Junjie Wu, Jiangtao Xie, Zhaolin Zhang, Qilong Wang, Qinghua Hu, Peihua Li, Sen Xu

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

Comments 14 pages

Scaling Language-Free Visual Representation Learning

David Fan, Shengbang Tong, Jiachen Zhu, Koustuv Sinha, Zhuang Liu, Xinlei Chen, Michael Rabbat, Nicolas Ballas, Yann LeCun, Amir Bar, Saining Xie

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

Comments Project page at https://davidfan.io/webssl/

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Xuan Wang, Siyuan Liang, Dongping Liao, Han Fang, Aishan Liu, Xiaochun Cao, Yu-liang Lu, Ee-Chien Chang, Xitong Gao

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

AnyTouch: Learning Unified Static-Dynamic Representation across Multiple Visuo-tactile Sensors

Ruoxuan Feng, Jiangyu Hu, Wenke Xia, Tianci Gao, Ao Shen, Yuhao Sun, Bin Fang, Di Hu

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

Comments Accepted by ICLR 2025

FlexiMo: A Flexible Remote Sensing Foundation Model

Xuyang Li, Chenyu Li, Pedram Ghamisi, Danfeng Hong

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

Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation

Alessio Borgi, Luca Maiano, Irene Amerini

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

Comments Accepted to the CVPR 2025 Workshop AI for Creative Visual Content Generation Editing and Understanding

FRAME: Floor-aligned Representation for Avatar Motion from Egocentric Video

Andrea Boscolo Camiletto, Jian Wang, Eduardo Alvarado, Rishabh Dabral, Thabo Beeler, Marc Habermann, Christian Theobalt

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

Comments Accepted at CVPR 2025

DSU-Net:An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement

Yimin Xu, Fan Yang, Bin Xu

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

Can language-guided unsupervised adaptation improve medical image classification using unpaired images and texts?

Umaima Rahman, Raza Imam, Mohammad Yaqub, Boulbaba Ben Amor, Dwarikanath Mahapatra

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

Comments Conference paper at International Symposium on Biomedical Imaging (ISBI) 2025

Enhancing Depression Detection via Question-wise Modality Fusion

Aishik Mandal, Dana Atzil-Slonim, Thamar Solorio, Iryna Gurevych

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

Comments 18 pages, 5 figures, The 10th Workshop on Computational Linguistics and Clinical Psychology

Inference-Time Policy Steering through Human Interactions

Yanwei Wang, Lirui Wang, Yilun Du, Balakumar Sundaralingam, Xuning Yang, Yu-Wei Chao, Claudia Perez-D'Arpino, Dieter Fox, Julie Shah

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

Comments ICRA 2025

Exploring Cultural Nuances in Emotion Perception Across 15 African Languages

Ibrahim Said Ahmad, Shiran Dudy, Tadesse Destaw Belay, Idris Abdulmumin, Seid Muhie Yimam, Shamsuddeen Hassan Muhammad, Kenneth Church

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

BIMII-Net: Brain-Inspired Multi-Iterative Interactive Network for RGB-T Road Scene Semantic Segmentation

Hanshuo Qiu, Jie Jiang, Ruoli Yang, Lixin Zhan, Jizhao Liu

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

TrafficLoc: Localizing Traffic Surveillance Cameras in 3D Scenes

Yan Xia, Yunxiang Lu, Rui Song, Oussema Dhaouadi, João F. Henriques, Daniel Cremers

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

MotionMap: Representing Multimodality in Human Pose Forecasting

Reyhaneh Hosseininejad, Megh Shukla, Saeed Saadatnejad, Mathieu Salzmann, Alexandre Alahi

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

Comments CVPR 2025. We propose a new representation for learning multimodality in human pose forecasting which does not depend on generative models

Task-driven Image Fusion with Learnable Fusion Loss

Haowen Bai, Jiangshe Zhang, Zixiang Zhao, Yichen Wu, Lilun Deng, Yukun Cui, Tao Feng, Shuang Xu

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

Comments Accepted to CVPR 2025

Exploring State Space Model in Wavelet Domain: An Infrared and Visible Image Fusion Network via Wavelet Transform and State Space Model

Tianpei Zhang, Yiming Zhu, Jufeng Zhao, Guangmang Cui, Yuchen Zheng

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

Unsupervised Foundation Model-Agnostic Slide-Level Representation Learning

Tim Lenz, Peter Neidlinger, Marta Ligero, Georg Wölflein, Marko van Treeck, Jakob Nikolas Kather

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

Comments Got accepted at CVPR 2025

Privacy-Preserving Federated Learning with Differentially Private Hyperdimensional Computing

Fardin Jalil Piran, Zhiling Chen, Mohsen Imani, Farhad Imani

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

Comments 31 Pages, 14 Figures

Fus-MAE: A cross-attention-based data fusion approach for Masked Autoencoders in remote sensing

Hugo Chan-To-Hing, Bharadwaj Veeravalli

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

Journal ref IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2024

GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects

Yizhe Liu, Tong Jia, Da Cai, Hao Wang, Dongyue Chen

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

Targetless 6DoF Calibration of LiDAR and 2D Scanning Radar Based on Cylindrical Occupancy

Weimin Wang, Yu Du, Ting Yang, Yu Liu

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

PE-CLIP: A Parameter-Efficient Fine-Tuning of Vision Language Models for Dynamic Facial Expression Recognition

Ibtissam Saadi, Abdenour Hadid, Douglas W. Cunningham, Abdelmalik Taleb-Ahmed, Yassin El Hillali

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

When Less is Enough: Adaptive Token Reduction for Efficient Image Representation

Eduard Allakhverdov, Elizaveta Goncharova, Andrey Kuznetsov

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

Comments 10 pages, 8 figures