Modern multimodal large language models (MLLMs) adopt a unified self-attention design that processes visual and textual tokens at every Transformer layer, incurring substantial computational overhead. In this work, we revisit the necessity of such dense visual processing and show that projected visual embeddings are already well-aligned with the language space, while effective vision-language interaction occurs in only a small subset of layers. Based on these insights, we propose ViCA (Vision-only Cross-Attention), a minimal MLLM architecture in which visual tokens bypass all self-attention and feed-forward layers, interacting with text solely through sparse cross-attention at selected layers. Extensive evaluations across three MLLM backbones, nine multimodal benchmarks, and 26 pruning-based baselines show that ViCA preserves 98% of baseline accuracy while reducing visual-side computation to 4%, consistently achieving superior performance-efficiency trade-offs. Moreover, ViCA provides a regular, hardware-friendly inference pipeline that yields over 3.5x speedup in single-batch inference and over 10x speedup in multi-batch inference, reducing visual grounding to near-zero overhead compared with text-only LLMs. It is also orthogonal to token pruning methods and can be seamlessly combined for further efficiency gains. Our code is available at https://github.com/EIT-NLP/ViCA.
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation
Department of Computer Science（计算机科学系）；University of North Carolina at Chapel Hill（北卡罗来纳大学 Chapel Hill 分校）；School of Artificial Intelligence and Data Science（人工智能与数据科学学院）；University of Science and Technology of China（中国科学技术大学）
From Image to Video, what do we need in multimodal LLMs?
Intelligent Computing and Machine Learning Lab, School of ASEE, Beihang University（北京航空航天大学自动化学院智能计算与机器学习实验室）；Xiaohongshu（小红书）；School of Sino-French Engineer, Beihang University（北京航空航天大学中法工程师学院）；College of Engineering and Computer Science, VinUniversity（Vin大学工程与计算机科学学院）
LLMs Meet Multimodal Generation and Editing: A Survey
The Hong Kong University of Science and Technology（香港科技大学）；The Chinese University of Hong Kong（香港中文大学）；Tsinghua University（清华大学）；Tencent AI Lab（腾讯AI实验室）
BLINK: Multimodal Large Language Models Can See but Not Perceive
University of Pennsylvania（宾夕法尼亚大学）；University of Washington（华盛顿大学）；Allen Institute for AI（艾伦人工智能研究所）；University of California, Davis（加利福尼亚大学戴维斯分校）；Columbia University（哥伦比亚大学）
DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
College of Artificial Intelligence, National Yang Ming Chiao Tung University（人工智能学院，阳明交通大学）；Institute of Population Health Sciences, National Health Research Institutes（人口健康科学研究所，国家健康研究院）；Department of Computer Science, National Yang Ming Chiao Tung University（计算机科学系，阳明交通大学）
ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicine
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Freedom AI；National Health Data Institute, Shenzhen（深圳国家健康数据研究院）；Shenzhen Research Institute of Big Data（深圳大数据研究院）；Guangdong University of Technology（广东工业大学）
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling
Harbin Institute of Technology, Shenzhen, China（哈尔滨工业大学（深圳））；Xiamen University Malaysia（厦门大学马来西亚分校）；Nanyang Technological University（南洋理工大学）；Beijing Academy of Artificial Intelligence, China（北京人工智能研究院）；Peng Cheng Laboratory, China（鹏城实验室）；Shaqra University, Saudi Arabia（沙迦大学）
How to Bridge the Gap between Modalities: Survey on Multimodal Large Language Model
College of Computer, National University of Defense Technology（国防科技大学计算机学院）；School of Computer and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）
Table Understanding and (Multimodal) LLMs: A Cross-Domain Case Study on Scientific vs. Non-Scientific Data
Deutsches Forschungszentrum für Künstliche Intelligenz GmbH (DFKI)（德国人工智能研究中心有限公司）；Technische Universität Berlin（柏林技术大学）；BIFOLD；Deutsche Telekom（德国电信）；Common Crawl Foundation（Common Crawl基金会）；Humboldt-Universität zu Berlin（柏林洪堡大学）
