Vision Transformers have emerged as powerful, scalable and versatile representation learners. To capture both global and local features, a learnable [CLS] class token is typically prepended to the input sequence of patch tokens. Despite their distinct nature, both token types are processed identically throughout the model. In this work, we investigate the friction between global and local feature learning under different pre-training strategies by analyzing the interactions between class and patch tokens. Our analysis reveals that standard normalization layers introduce an implicit differentiation between these token types. Building on this insight, we propose specialized processing paths that selectively disentangle the computational flow of class and patch tokens, particularly within normalization layers and early query-key-value projections. This targeted specialization leads to significantly improved patch representation quality for dense prediction tasks. Our experiments demonstrate segmentation performance gains of over 2 mIoU points on standard benchmarks, while maintaining strong classification accuracy. The proposed modifications introduce only an 8% increase in parameters, with no additional computational overhead. Through comprehensive ablations, we provide insights into which architectural components benefit most from specialization and how our approach generalizes across model scales and learning frameworks.
Frozen Foundation-Model Embeddings Discard Small-Lesion Signal in Chest Radiography: Implications for Pre-Deployment Evaluation
Department of Biomedical Engineering and Informatics, Indiana University（印第安纳大学生物医学工程与信息学系）；Department of Radiology and Imaging Sciences, Emory University（埃默里大学放射学与影像科学系）
Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors
PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学PCA实验室）；PCA Lab, School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学PCA实验室）
Revisiting the Role of Foundation Models in Cell-Level Histopathological Image Analysis under Small-Patch Constraints -- Effects of Training Data Scale and Blur Perturbations on CNNs and Vision Transformers
Division of Gastrointestinal Surgery, Department of Surgery, Kobe University Graduate School of Medicine（Kobe大学医学研究院外科部胃肠外科部）；Association of Medical Artificial Intelligence Curation（医学人工智能 curation协会）；Center for Medical Education and Clinical Training, Kindai University Faculty of Medicine（Kindai大学医学部医学教育与临床培训中心）；Department of Biophysics, Kobe University Graduate School of Health Sciences（Kobe大学健康科学研究院生物物理学部）
Don't Just Chase "Highlighted Tokens" in MLLMs: Revisiting Visual Holistic Context Retention
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；The Hong Kong University of Science and Technology（香港科学与技术大学）；Shanghai Jiao Tong University（上海交通大学）
Unlocking Patch-Level Features for CLIP-Based Class-Incremental Learning
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学软件新技术国家重点实验室）
Multimodal Fusion Transformer for Remote Sensing Image Classification
Jalpaiguri Government Engineering College（贾尔派古里政府工程学院）；Technical University of Munich（慕尼黑工业大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）；Helmholtz-Zentrum Dresden-Rossendorf（亥姆霍兹德累斯顿罗森多夫研究中心）；University of Extremadura（埃斯特雷马杜拉大学）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；CNRS（法国国家科学研究中心）；Grenoble INP（格勒诺布尔国立理工学院）
From Pixels to Tokens: Revisiting Object Hallucinations in Large Vision-Language Models
University of Chinese Academy of Sciences（中国科学院大学）；Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua University（计算机科学与技术系，人工智能研究院，清华大学）；Gaoling School of Artificial Intelligence, Renmin University of China（人工智能学院，中国人民大学）；Kuaishou Technology Inc.（快手科技有限公司）；Shanghai Key Laboratory of Multi. Info. Processing, East China Normal University（多信息处理重点实验室，华东师范大学）
Revisiting Shadow Detection from a Vision-Language Perspective
CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China（中国科学技术大学地球空间信息处理与应用系统重点实验室，电子工程与信息科学系）
Zhejiang Lab（之江实验室）；School of Computer Science and Information Engineering, Hefei University of Technology（合肥工业大学计算机与信息工程学院）；School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院）；School of Automation, Northwestern Polytechnical University（西北工业大学自动化学院）
BGG: Bridging the Geometric Gap between Cross-View images by Vision Foundation Model Adaptation for Geo-Localization
Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University（中国教育部智能感知与图像理解重点实验室，西安电子科技大学）；School of Telecommunications, Xidian University（西安电子科技大学电信学院）；Department of Automation, Tsinghua University（清华大学自动化系）
SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning
Peking University（北京大学）；MIT（麻省理工学院）；TUM（技术大学（TUM））；Meituan（美团）；Peking University School of CIT, MCML, MDSIEECS and CSAIL（北京大学计算机学院、MCML、MDSIEECS以及CSAIL）
From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-Identification
Department of Electrical and Computer Engineering, University of Washington（华盛顿大学电气与计算机工程系）；Applied Physics Laboratory, University of Washington（华盛顿大学应用物理实验室）
Mobile U-ViT: Revisiting large kernel and U-shaped ViT for efficient medical image segmentation
University of Science and Technology of China（中国科学技术大学）；Suzhou Institute for Advanced Research, USTC（苏州先进研究院）；Shanghai Jiao Tong University（上海交通大学）；Harbin Institute of Technology（哈尔滨工业大学）；State Grid Hunan ElectricPower Corporation Limited Research Institute（国网湖南电力有限公司研究院）
Embedding Radiomics into Vision Transformers for Multimodal Medical Image Classification
Duke Kunshan University（昆山杜克大学）；Jiangsu Provincial University Key (Construction) Laboratory for Smart Diagnosis and Treatment of Lung Cancer（江苏省高校重点（建设）实验室肺癌智能诊疗实验室）；The First People’s Hospital of Kunshan（昆山市第一人民医院）；Duke University（杜克大学）
