Model Specific Task Similarity for Vision Language Model Selection via Layer Conductance
School of Computer Science and Technology, University of Science and Technology of China（计算机科学与技术学院，科学技术大学）；School of AI and Data Science, University of Science and Technology of China（人工智能与数据科学学院，科学技术大学）
Wei Yang, Hong Xie, Tao Tan, Xin Li, Defu Lian, Enhong Chen
While open sourced Vision-Language Models (VLMs) have proliferated, selecting the optimal pretrained model for a specific downstream task remains challenging. Exhaustive evaluation is often infeasible due to computational constraints and data limitations in few shot scenarios. Existing selection methods fail to fully address this: they either rely on data-intensive proxies or use symmetric textual descriptors that neglect the inherently directional and model-specific nature of transferability. To address this problem, we propose a framework that grounds model selection in the internal functional dynamics of the visual encoder. Our approach represents each task via layer wise conductance and derives a target-conditioned block importance distribution through entropy regularized alignment. Building on this, we introduce Directional Conductance Divergence (DCD), an asymmetric metric that quantifies how effectively a source task covers the target's salient functional blocks. This allows for predicting target model rankings by aggregating source task ranks without direct inference. Experimental results on 48 VLMs across 21 datasets demonstrate that our method outperforms state-of-the-art baselines, achieving a 14.7% improvement in NDCG@5 over SWAB.
Geometric Similarity in VLM Low-Level Vision Representations
Duke University（杜克大学）；Texas A&M University（德克萨斯A&M大学）；Florida State University（佛罗里达州立大学）；UC San Diego（加州大学圣迭戈分校）；University of Pennsylvania（宾夕法尼亚大学）；UNC Chapel Hill（北卡罗来纳大学教堂山分校）
Can Vision-Language Models Understand and Interpret Dynamic Gestures from Pedestrians? Pilot Datasets and Exploration Towards Instructive Nonverbal Commands for Cooperative Autonomous Vehicles
University of California Merced（加州大学默塞德分校）；Aalborg University（奥尔堡大学）
PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Purple Mountain Laboratories（紫金山实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）
REVEAL++: Differentiable Phenotypic Grouping for Vision-Language Retinal Modeling of Alzheimer's Disease Risk
University of Virginia（弗吉尼亚大学）；J. Crayton Pruitt Family Department of Biomedical Engineering, Herbert Wertheim College of Engineering, University of Florida（佛罗里达大学赫伯特·韦特海姆工程学院J. Crayton Pruitt家庭生物医学工程系）
