Overview

Cross-modal attention studies how information from one modality—such as text, images, audio, video, or sensor data—can guide the representation of another. It matters for tasks including visual question answering, retrieval, medical diagnosis, speech separation, and autonomous systems, where useful evidence may be distributed across inputs. Common approaches include bidirectional or asymmetric cross-attention, query- and register-based fusion, and sparse, local, or temporally guided attention, sometimes combined with confidence gating or feature disentanglement. Performance has improved across many benchmarks, but reliable fusion remains difficult when modalities are misaligned, unevenly informative, or prone to dominating one another; attention patterns also do not always guarantee faithful grounding or reasoning.

Latest papers

CardsList

93 papers4 papers in the last four weeks, down 60% on the four weeks before. 0.0% of all new papers.

  1. Beyond Parallel Tracking: Interactive Multi-Feature Fusion Drives Semantic Reconstruction from Non-invasive Brain Recordings

    Jul 13, 2026Boda Xiao, Xiran Xu, Songyi Li +4Neural DecodingBrain-to-Speech Decoding

  2. Learning to Unify Deformable Shape and Texture Representations for Cardiac Video Classification

    Jul 8, 2026Tonmoy Hossain, Miaomiao ZhangGeometric Representation LearningMedical Image Classification

  3. AT-Attn: Temporal-Aware Cross-Attention for Longitudinal Multimodal Alzheimer's Disease Diagnosis

    Jul 8, 2026Xinyue Du, Yibo Liu, Zhenglei Zhou +3Alzheimer's DiseaseLongitudinal Medical Image Analysis

  4. ELSA3D: Elastic Semantic Anchoring for Unified 3D Understanding and Generation

    Jul 7, 2026Tianjiao Yu, Xinzhuo Li, Yifan Shen +43D Foundation ModelsUnified Multimodal Models

  5. Q-TriM: Question-Guided Tri-Modal Attention for Audio-Visual Question Answering

    Jul 4, 2026SungHun Kim, SeungJun BaekMultimodal QACross-Modal Attention

  6. ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs

    Jun 30, 2026Zhiyuan Yao, Zheren Fu, Zhixiao Zheng +3Cross-AttentionDirect Preference Optimization

  7. Modeling Local, Global, and Cross-Modal Context in Multimodal 3D MRI

    Jun 25, 2026Minh Duc Do, Tillmann Rheude, Noel Kronenberg +23D ViTsBrain Age Prediction

  8. Multi-modality Image Fusion under Adverse Weather: Mask-Guided Feature Restoration and Interaction

    Jun 25, 2026Xilai Li, Xiaosong Li, Haishu Tan +3Multi-Source Image FusionCross-Modal Attention

  9. Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection

    Jun 23, 2026Tian Qiu, Jifeng Shen, Xin ZuoCross-Modal AttentionCross-Modal Alignment

  10. Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs

    Jun 22, 2026Chuangxin Zhao, Canran Xiao, Siyuan Ma +5Visual Question AnsweringCross-Modal Attention

  11. Text Dictates, Music Decorates: Energy-based Attention for Editable Dance Motion Generation

    Jun 22, 2026Seong Jong Yoo, Siyuan Peng, Felix Gu +2Diffusion TransformerText-to-Motion Generation

  12. DREAM: Extending Vision-Language Models with Dual-Objective Encoding for Cross-Modal Retrieval

    Jun 17, 2026Kaleem Ullah, Altaf Hussain, Muhammad Munsif +1Cross-Modal RetrievalVideo Representation Learning

  13. Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention

    Jun 8, 2026George Theodosiou, Loukas Ilias, Dimitris AskounisAudio Representation LearningParkinson's Disease Detection from Speech

  14. DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning

    Jun 6, 2026Hangui Lin, Yan Shu, Zhengyang Liang +8Cross-Modal AlignmentVLM Reasoning

  15. UniCA: Bi-directional Cross-Attention with Positive Similarity Loss for Robust Multi-Modal Retrieval

    Jun 3, 2026Yini Huang, Wenlong ZhangMultimodal IRCross-Modal Alignment

  16. Query-based Cross-Modal Projector Bolstering Mamba Multimodal LLM

    Jun 3, 2026SooHwan Eom, Jay Shim, Gwanhyeong Koo +4MambaEfficient VLM Inference

  17. MOSS-Video-Preview: Toward Real-Time Video Understanding via Cross-Attention

    Jun 1, 2026Pengyu Wang, Chenkun Tan, Shaojun Zhou +18Streaming Video UnderstandingEfficient VLM Inference

  18. CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning

    Jun 1, 2026Dong Li, Lingling Zhang, Binghao Han +2Missing-Modality LearningCross-Modal Attention

  19. MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance

    May 29, 2026Nathan Sala, Ofir Abramovich, Ariel Shamir +3Text-to-Motion GenerationCross-Modal Attention

  20. Vision-Language Binding in In-Context Image Generation

    May 23, 2026Chris Ge, Rohit Gandikota, Antonio Torralba +1Image GenerationMechanistic Interpretability

  21. Correcting Visual Blur Induced by Attention Distraction to Reduce Hallucinations: Algorithm and Theory

    May 23, 2026Quanjiang Li, Zhiming Liu, Wei Luo +2LLM Hallucination MitigationHallucination in Language Models

  22. MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues

    May 21, 2026Dazhao Du, Liao Duan, Jian Liu +5Temporal Video GroundingMultimodal Large Language Models

  23. RAVE: Re-Allocating Visual Attention in Large Multimodal Models

    May 18, 2026Xi Leng, Xinhong Ma, Ziqiang Dong +4Visual AttentionSelf-Attention

  24. CAM-VFD: Cross-Attention Multimodal Video Forgery Detection

    May 16, 2026Hoda Osama Elkhodary, Sherin Mostafa Youssef, Marwa Elshenawy +1Multimodal Deepfake DetectionMultimodal Robustness

  25. MHSA: A Lightweight Framework for Mitigating Hallucinations via Steered Attention in LVLMs

    May 14, 2026Wei Ding, Yilin Li, Yudong Zhang +4Vision-Language ModelsLLM Hallucination Mitigation

  26. FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth

    May 8, 2026Zhixin Cheng, Yujia Chen, Xujing Tao +4Cross-Modal AttentionPoint Cloud Registration

  27. PRIMED: Adaptive Modality Suppression for Referring Audio-Visual Segmentation via Biased Competition

    May 8, 2026Yuchen He, Jing ZhangAudio-Visual UnderstandingReferring Expression Segmentation

  28. PC-MNet: Dual-Level Congruity Modeling for Multimodal Sarcasm Detection via Polarity-Modulated Attention

    May 4, 2026Maoheng Li, Ling Zhou, Xiaohua Huang +3Cross-Modal AttentionMultimodal Fusion