University of Oxford（牛津大学）

Trust in Vision-Language Models: Insights from a Participatory User Workshop

Agnese Chiatti, Lara Piccolo, Sara Bernardini, Matteo Matteucci, Viola Schiaffonati

机构 * University of Oxford, UK（牛津大学） ； CODE University of Applied Sciences, Germany（应用科学学院） 纠错

Journal ref Proceedings of the The European Workshop on Trustworthy AI (Trust-AI) at ECAI 2025

Cognitive Maps in Language Models: A Mechanistic Analysis of Spatial Planning

Caroline Baumgartner, Eleanor Spens, Neil Burgess, Petru Manescu

机构 * University College London（伦敦大学学院） ； University of Oxford（牛津大学） 纠错

Training Instabilities Induce Flatness Bias in Gradient Descent

Lawrence Wang, Stephen J. Roberts

机构 * Department of Engineering, University of Oxford（牛津大学工程系） 纠错

Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles

Rhys Howard, Nick Hawes, Lars Kunze

机构 * Oxford Robotics Institute, Dept. of Eng. Sci., University of Oxford（牛津大学机器人研究所） 纠错

Comments 8 Pages, 5 Figures, To be published in the Proceedings of the 2025 IEEE International Conference on Robotics & Automation, Initial upload of accepted paper

Journal ref 2025 IEEE International Conference on Robotics and Automation (ICRA), Atlanta, GA, USA, 2025

Towards Collective Intelligence: Uncertainty-aware SAM Adaptation for Ambiguous Medical Image Segmentation

Mingzhou Jiang, Jiaying Zhou, Junde Wu, Tianyang Wang, Yueming Jin, Min Xu

机构 * Department of Computer Science, The University of Alabama at Birmingham（阿拉巴马大学伯明翰分校计算机科学系） ； Doctoral Training Centre, University of Oxford（牛津大学博士培训中心） ； Department of Biomedical Engineering and Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学生物医学工程系和电气与计算机工程系） ； Computational Biology Department, Carnegie Mellon University（卡内基梅隆大学计算生物学系） ； Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学） 纠错

Achieving Fairness with a Simple Ridge Penalty

Marco Scutari, Francesca Panero, Manuel Proissl

机构 * M. Scutari Istituto Dalle Molle di Studi sull'Intelligenza Artificiale (IDSIA), Lugano, Switzerland F. Panero London School of Economics ； formerly Department of Statistics, University of Oxford, Oxford, United Kingdom M. Proissl UBS, Data \& Analytics Center of Excellence, Zurich, Switzerland 纠错

Comments 16 pages, 9 figures

Journal ref Statistics and Computing (2022), 32, 77

Sound Logical Explanations for Mean Aggregation Graph Neural Networks

Matthew Morris, Ian Horrocks

机构 * Department of Computer Science University of Oxford（计算机科学系牛津大学） 纠错

Comments Full version (with appendices) of paper accepted to NeurIPS 2025 (The Thirty-Ninth Annual Conference on Neural Information Processing Systems)

Beyond H&E: Unlocking Pathological Insights with Polarization Imaging

Yao Du, Jiaxin Zhuang, Xiaoyu Zheng, Jing Cong, Limei Guo, Chao He, Lin Luo, Xiaomeng Li

机构 * The Hong Kong University of Science and Technology（香港科技大学） ； Beijing Institute of Collaborative Innovation（北京协同创新研究院） ； Peking University Health Science Center, Peking University Third Hospital（北京大学人民医院） ； University of Oxford（牛津大学） ； Peking University（北京大学） 纠错

Comments Accepted as a regular paper at IEEE BIBM 2025