Visual prompting techniques are widely used to efficiently fine-tune pretrained Vision Transformers (ViT) by learning a small set of shared prompts for all tokens. However, existing methods overlook the unique roles of different tokens in conveying discriminative information and interact with all tokens using the same prompts, thereby limiting the representational capacity of ViT. This often leads to indistinguishable and biased prompt-extracted features, hindering performance. To address this issue, we propose a plug-and-play Token Coordinated Prompt Attention (TCPA) module, which assigns specific coordinated prompts to different tokens for attention-based interactions. Firstly, recognizing the distinct functions of CLS and image tokens-global information aggregation and local feature extraction, we disentangle the prompts into CLS Prompts and Image Prompts, which interact exclusively with CLS tokens and image tokens through attention mechanisms. This enhances their respective discriminative abilities. Furthermore, as different image tokens correspond to distinct image patches and contain diverse information, we employ a matching function to automatically assign coordinated prompts to individual tokens. This enables more precise attention interactions, improving the diversity and representational capacity of the extracted features. Extensive experiments across various benchmarks demonstrate that TCPA significantly enhances the diversity and discriminative power of the extracted features. The code is available at https://github.com/zhoujiahuan1991/ICML2025-TCPA.
Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；vivo Mobile Communication Co., Ltd.（维沃移动通信有限公司）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；Pengcheng Laboratory（鹏城实验室）
Key Laboratory of Intelligent Information Processing, ICT, CAS（中国科学院计算技术研究所智能信息处理重点实验室）；Beijing Academy of Artificial Intelligence（北京智源人工智能研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Multigrain-aware Semantic Prototype Scanning and Tri-Token Prompt Learning Embraced High-Order RWKV for Pan-Sharpening
Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Yunnan Normal University, Ministry of Education（云南师范大学教育部）；Xidian University（西安电子科技大学）；University of Science and Technology of China（中国科学技术大学）；The Hong Kong University of Science and Technology（香港理工大学）；MoE Key Laboratory of Information Technology（教育部信息科学技术重点实验室）
PM2: A New Prompting Multi-modal Model Paradigm for Few-shot Medical Image Classification
Dalian University of Technology（大连理工大学）；School of Computer Science and Technology（计算机科学与技术学院）；School of Computer Science and Engineering（计算机科学与工程学院）；Dalian Minzu University（大连民族大学）；School of Information and Communication Engineering（信息与通信工程学院）
State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
Wangxuan Institute of Computer Technology, Peking University（北京大学王轩计算机技术研究所）；the Huazhong University of Science and Technology（华中科技大学）；Amazon.com, Inc（亚马逊公司）
How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China（东北大学计算机科学与工程学院，沈阳 110819，中国）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；School of Computer and Communication Engineering, Northeastern University, Qinhuangdao 066004, China（东北大学计算机与通信工程学院，秦皇岛 066004，中国）
