When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks
当更强的触发器反噬:高维背景下后门攻击的理论
Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating, Inbar Seroussi
机构
*
Mathematical Institute, University of Oxford(牛津大学数学研究所)
;
School of Mathematical Science, Tel Aviv University(特拉维夫大学数学科学学院)
;
School of Mathematical Science and Computer Science, Tel Aviv University(特拉维夫大学数学科学与计算机科学学院)
Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces
黎曼几何与fMRI的结合:建模相关流形和特征向量子空间的优势
Mario Severino, Manuela Moretto, Robert A. McCutcheon, Mattia Veronese
机构
*
Department of Information Engineering, University of Padova(信息工程系,帕多瓦大学)
;
Department of Neuroimaging, Institute of Psychiatry, Psychology and Neuroscience (IoPPN), King’s College London(神经影像系,精神病学、心理学与神经科学研究所(IoPPN),伦敦国王学院)
;
Department of Psychiatry, University of Oxford(精神病学系,牛津大学)
;
Oxford Health NHS Foundation Trust, Warneford Hospital(牛津健康国家卫生信托基金,沃内福德医院)
;
Department of Psychosis Studies, Institute of Psychiatry, Psychology and Neuroscience, King’s College London(精神病学研究系,精神病学、心理学与神经科学研究所,伦敦国王学院)
No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation
没有比现在更严峻的挑战:鲁棒的气候模拟需要分布外泛化
Bradley Stanley-Clamp, Anson Lei, Hannah M. Christensen, Ingmar Posner
机构
*
Applied AI Lab University of Oxford, UK(应用人工智能实验室,牛津大学,英国)
;
Atmospheric, Oceanic and Planetary Physics University of Oxford, UK(大气、海洋和行星物理,牛津大学,英国)
Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
通过局部可塑性和树突计算进行源分离的规范网络
Bariscan Bozkurt, Efe Ali Gorguner, Francesco Innocenti, Rafal Bogacz
机构
*
Gatsby Computational Neuroscience Unit, University College London, UK(Gatsby计算神经科学单元,伦敦大学学院,英国)
;
Department of Computer Science, University of Oxford, UK(计算机科学系,牛津大学,英国)
;
Brain Network Dynamics Unit, University of Oxford, UK(脑网络动力学单元,牛津大学,英国)
;
MRC Centre of Research Excellence in Restorative Neural Dynamics, UK(英国医学研究委员会修复神经动力学研究卓越中心)
Dynamic Mixture of Latent Memories for Self-Evolving Agents
动态潜在记忆混合用于自演化智能体
Dianzhi Yu, Vireo Zhang, Hongru Wang, Yanyu Chen, Minda Hu, Wanghan Xu, Siki Chen, Philip Torr, Zhenfei Yin, Irwin King
机构
*
The Chinese University of Hong Kong(香港中文大学)
;
University of Oxford(牛津大学)
;
Nanyang Technological University(南洋理工大学)
;
University of Edinburgh(爱丁堡大学)
;
Shanghai Jiao Tong University(上海交通大学)
Learning to Evolve: Multi-modal Interactive Fields for Robust Humanoid Navigation in Dynamic Environments
学习进化:多模态交互场用于动态环境中的稳健双足机器人导航
Peifeng Jiang, Hong Liu, Jin Jin, Wenshuai Wang, Xia Li
机构
*
State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School(一般人工智能国家重点实验室,北京大学深圳研究生院)
;
Oxford Robotics Institute, University of Oxford(牛津大学机器人研究所)
;
Institute for Machine Learning, Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系机器学习研究所)
stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation
stable-worldmodel: 一个用于可重复世界建模研究和评估的平台
Lucas Maes, Quentin Le Lidec, Luiz Facury, Nassim Massaudi, Ayush Chaurasia, Francesco Capuano, Richard Gao, Taj Gillin, Dan Haramati, Damien Scieur, Yann LeCun, Randall Balestriero
机构
*
Mila & Université de Montréal(Mila与蒙特利尔大学)
;
New York University(纽约大学)
;
Universidade Federal de Minas Gerais(巴西联邦大学矿务学院)
;
Independent Researcher(独立研究者)
;
LanceDB
;
University of Oxford(牛津大学)
;
Brown University(布朗大学)
What Counts as AI Sycophancy? A Taxonomy and Expert Survey of a Fragmented Construct
什么是AI阿谀奉承?对一个碎片化概念的分类和专家调查
Meryl Ye, Lujain Ibrahim, Jessica Y. Bo, Myra Cheng, Ida Mattsson, Daniel Vennemeyer, Robert Kraut, Steve Rathje
机构
*
Carnegie Mellon University(卡内基梅隆大学)
;
University of Oxford(牛津大学)
;
University of Toronto(多伦多大学)
;
Stanford University(斯坦福大学)
;
University of Cincinnati(克里夫兰医学中心大学)
;
New York University(纽约大学)
Richer Bayesian Last Layers with Subsampled NTK Features
更丰富的贝叶斯最后层与子采样NTK特征
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna, Álvaro Cartea, Yarin Gal, Jose Miguel Hernández-Lobato, Kamil Ciosek
机构
*
Mathematical Institute, University of Oxford(牛津大学数学研究所)
;
Oxford-Man Institute, University of Oxford(牛津大学奥克斯曼研究所)
;
OATML, University of Oxford(牛津大学OATML研究所)
;
Department of Engineering, University of Cambridge(剑桥大学工程系)
From monoliths to modules: Decomposing transducers for efficient world modelling
从整体到模块:分解转换器以实现高效的world建模
Alexander Boyd, Franz Nowak, David Hyland, Manuel Baltieri, Fernando E. Rosas
机构
*
Department of Informatics, University of Sussex(Sussex大学信息学院)
;
Beyond Institute for Theoretical Science (BITS)(理论科学研究所)
;
ETH Zürich(苏黎世联邦理工学院)
;
Principles of Intelligent Behaviour in Biological and Social Systems (PIBBSS)(生物和社会系统智能行为原理研究所)
;
Department of Computer Science, University of Oxford(牛津大学计算机科学系)
;
Araya Inc.(Araya公司)
;
Sussex AI and Sussex Centre for Consciousness Science, University of Sussex(Sussex大学人工智能与意识科学中心)
;
Centre for Complexity Science and Center for Psychedelic Research, Department of Brain Sciences, Imperial College London(复杂科学中心和迷幻研究中心,伦敦帝国理工学院脑科学系)
;
Center for Eudaimonia and Human Flourishing, University of Oxford(幸福与人类繁荣中心,牛津大学)
A KL-regularization Framework for Learning to Plan with Adaptive Priors
一种基于KL正则化的学习规划框架:具有自适应先验的规划
Álvaro Serra-Gomez, Daniel Jarne Ornia, Dhruva Tirumala, Thomas Moerland
机构
*
LIACS, Leiden University, Leiden, The Netherlands(莱顿大学莱顿分校,荷兰)
;
Google Deepmind, London, United Kingdom(谷歌DeepMind,英国伦敦)
;
University of Oxford, Oxford, United Kingdom(牛津大学,英国牛津)