Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we begin from the Iso-Energy Assumption, which exploits cross-modal redundancy: a concept that is truly shared should exhibit the same average energy across modalities. We operationalize this assumption with an Aligned Sparse Autoencoder (SAE) that encourages energy consistency during training while preserving reconstruction. We find that this inductive bias changes the SAE solution without harming reconstruction, giving us a representation that serves as a tool for geometric analysis. Sanity checks on controlled data with known ground truth confirm that alignment improves when Iso-Energy holds and remains neutral when it does not. Applied to foundational VLMs, our framework reveals a clear structure with practical consequences: (i) sparse bimodal atoms carry the entire cross-modal alignment signal; (ii) unimodal atoms act as modality-specific biases and fully explain the modality gap; (iii) removing unimodal atoms collapses the gap without harming performance; (iv) restricting vector arithmetic to the bimodal subspace yields in-distribution edits and improved retrieval. These findings suggest that the right inductive bias can both preserve model fidelity and render the latent geometry interpretable and actionable.
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）；Xiaohongshu Inc.（小红书公司）；Shanghai Jiao Tong University（上海交通大学）
Investigating Redundancy in Multimodal Large Language Models with Multiple Vision Encoders
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Zhejiang University（浙江大学）；Beijing University of Technology（北京工业大学）
Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
UVLab, Department of Computer Science, University of Warwick（华威大学计算机科学系UVLab）；Department of Automation, University of Cambridge（剑桥大学自动化系）；Department of Computer Science, The University of Sheffield（谢菲尔德大学计算机科学系）
Skip-It? Theoretical Conditions for Layer Skipping in Vision-Language Models
Department of Electrical and Computer Engineering, The University of Illinois, Champaign, IL, United States（电气与计算机工程系，伊利诺伊大学香槟分校）；Department of Mathematics, The University of Illinois, Champaign, IL, United States（数学系，伊利诺伊大学香槟分校）；AI Innovation Institute, Stony Brook University, Stony Brook, NY, United States（人工智能创新研究所，石溪大学）
Libra: Building Decoupled Vision System on Large Language Models
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of the Chinese Academy of Sciences（中国科学院大学人工智能学院）；Peng Cheng Laboratory（鹏城实验室）
FLARE: Fully Integration of Vision-Language Representations for Deep Cross-Modal Understanding
Peking University Shanghai AI Laboratory（北京大学上海人工智能实验室）；Nanjing University（南京大学）；Peking University（北京大学）；Shanghai AI Laboratory（上海人工智能实验室）；Zhongguancun Academy Beijing Key Laboratory of Data Intelligence and Security（中关村北京数据智能与安全重点实验室）
3D Modality-Aware Pre-training for Vision-Language Model in MRI Multi-organ Abnormality Detection
School of Electronic, Electrical Engineering and Physics, Fujian University of Technology（福建工程学院电子电气工程学院）；School of Computer Science and Engineering, Southeast University, China（东南大学计算机科学与工程学院）；Department of Medical Imaging, Suzhou Traditional Chinese Medicine Hospital, China（苏州中医医院影像科）
Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Kuaishou Technology（快手科技）；CAIR, HKISI, Chinese Academy of Sciences（中国科学院香港创新研究院人工智能与机器人创新中心）
Breaking Modality Heterogeneity in Low-Bit Quantization for Large Vision-Language Models
VCIP, College of Computer Science, Nankai University（南开大学计算机科学学院VCIP）；D-ITET, ETH Zürich（苏黎世联邦理工学院D-ITET）；OPPO Research Institute（OPPO研究院）；Department of Computing, Hong Kong Polytechnic University（香港理工大学计算机系）
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
School of Software Engineering, Huazhong University of Science and Technology（华中科技大学软件学院）；Nanyang Technological University, Singapore（新加坡南洋理工大学）；University College London（伦敦大学学院）
MedPruner: Training-Free Hierarchical Token Pruning for Efficient 3D Medical Image Understanding in Vision-Language Models
Chinese University of Hong Kong（香港中文大学）；Westlake University（西湖大学）；Southern Medical University（南方医科大学）；Jiangnan University（江南大学）；Dalian University of Technology（大连理工大学）；Shanghai Jiao Tong University（上海交通大学）；University of Copenhagen（哥本哈根大学）
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
Peking University（北京大学）；School of Software and Microelectronics, Peking University（北京大学软件与微电子学院）；BIGAI（北京智源人工智能研究院）；Paul G. Allen School of Computer Science and Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）；Beijing Jiaotong University（北京交通大学）
RaP: Redundancy-aware Video-language Pre-training for Text-Video Retrieval
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）；Kuaishou Technology（快手科技）
Peeling the Onion: Hierarchical Reduction of Data Redundancy for Efficient Vision Transformer Training
Northeastern University（东北大学）；University of California, Irvine（加州大学欧文分校）；Peking university（北京大学）；ETH Zurich（苏黎世联邦理工学院）；Western Digital Research（西部数据研究院）；Unversity of Texas at Austin（德克萨斯大学奥斯汀分校）；Clemson University（克莱姆森大学）
