arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

Imperial College London(帝国理工学院)

共收录 1182
2601.07093 2026-03-05 cs.CV cs.AI

3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising

基于3D小波的结构先验用于控制扩散的全身体低剂量PET去噪

Peiyuan Jing, Yue Yang, Chun-Wun Cheng, Zhenxuan Zhang, Liutao Yang, Thiago V. Lima, Klaus Strobel, Antoine Leimgruber, Angelica Aviles-Rivero, Guang Yang, Javier A. Montoya-Zegarra

机构 * School of Engineering, Zurich University of Applied Sciences, CH Bioengineering Department Imperial-X, Imperial College London, UK DAMTP, University of Cambridge, UK Lucerne University Teaching Research Hospital, CH Lung Institute, Imperial College London, UK Cardiovascular Research Centre, Royal Brompton Hospital, UK School of Biomedical Engineering \& Imaging Sciences, King's College London, UK Yau Mathematical Sciences Center, Tsinghua University, CN

AI总结 WCC-Net通过引入3D小波结构先验,提升低剂量PET去噪效果,实现更稳定的解剖结构与噪声分离。

Comments 10 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.01138 2026-03-05 eess.SP cs.LG

Graph Neural Networks in EEG-based Emotion Recognition: A Survey

基于EEG的情感识别中的图神经网络:综述

Chenyu Liu, Yuqiu Deng, Yihao Wu, Ruizhi Yang, Zhongruo Wang, Liangwei Zhang, Siyun Chen, Tianyi Zhang, Yang Liu, Yi Ding, Liming Zhai, Ziyu Jia, Xinliang Zhou

机构 * Nanyang Technological University, Singapore(南洋理工大学) Xi’an Jiaotong University, Xi’an, China(西安交通大学) Imperial College London, London, UK(伦敦帝国理工学院) Amazon, Seattle, WA, USA(亚马逊) Carnegie Mellon University, Pittsburgh, PA, USA(卡内基梅隆大学) Uber Technologies, Inc., USA(Uber Technologies, Inc.) School of Computer Science, Central China Normal University, Wuhan, China(中央财经大学计算机学院) Institute of Automation, Chinese Academy of Sciences, Beijing, China(中国科学院自动化研究所)

AI总结 本文综述了基于EEG的情感识别中图神经网络的应用,分析了现有方法的共性与差异,并探讨了未来研究方向。

Comments The 30th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01073 2026-03-04 cs.CV

Flow Matching-enabled Test-Time Refinement for Unsupervised Cardiac MR Registration

基于流匹配的无监督心脏磁共振成像测试时细化

Yunguan Fu, Wenjia Bai, Wen Yan, Matthew J Clarkson, Rhodri Huw Davies, Yipeng Hu

机构 * University College London(伦敦大学学院) InstaDeep Imperial College London(伦敦帝国学院)

AI总结 FlowReg 通过流匹配框架实现高效的无监督心脏 MR 配准,无需预训练模型,提升配准精度并减少误差

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02452 2026-03-04 cs.LG cs.AI stat.ML

Manifold Aware Denoising Score Matching (MAD)

面向流形的去噪分数匹配(MAD)

Alona Levy-Jurgenson, Alvaro Prat, James Cuin, Yee Whye Teh

机构 * Department of Statistics University of Oxford(牛津大学统计系) Department of Mathematics, Imperial College London, London, United Kingdom(伦敦帝国理工学院数学系)

AI总结 本文提出了一种面向流形的去噪分数匹配方法,通过分解分数函数来隐式考虑流形,从而减少计算负担并提高效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.12274 2026-03-04 cs.LG physics.geo-ph

Function-Space Decoupled Diffusion for Forward and Inverse Modeling in Carbon Capture and Storage

函数空间解耦扩散用于碳捕集与封存的正反演建模

Xin Ju, Jiachen Yao, Anima Anandkumar, Sally M. Benson, Gege Wen

机构 * Stanford University(斯坦福大学) California Institute of Technology(加州理工学院) Imperial College London(伦敦帝国学院)

AI总结 函数空间解耦扩散方法在碳捕集与封存的正反演建模中实现高效且物理一致的参数恢复与数据同化。

Comments Accepted to ICLR AI&PDE Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.09143 2026-03-04 cs.LG cs.NA math.NA physics.comp-ph

Discrete Solution Operator Learning for Geometry-Dependent PDEs

几何依赖偏微分方程的离散解算子学习

Jinshuai Bai, Haolin Li, Zahra Sharif Khodaei, M. H. Aliabadi, YuanTong Gu, Xi-Qiao Feng

机构 * Institute of Biomechanics and Medical Engineering Applied Mechanics Laboratory (AML) Tsinghua University(生物力学与医学工程研究所应用力学实验室(AML)清华大学) Department of Aeronautics Imperial College London(航空航天系帝国理工学院伦敦) School of Mechanical, Medical, and Process Engineering Queensland University of Technology(机械、医学与工艺工程学院昆士兰理工大学)

AI总结 DiSOL通过学习离散求解过程来处理几何依赖的偏微分方程,实现稳定且准确的预测。

Comments 15 pages main text, 42 pages SI

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00272 2026-03-04 cs.LG cs.AI cs.CR

WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols

WARP:用于攻击鲁棒删除学习协议的权重传送

Mohammad M Maheri, Xavier Cadet, Peter Chin, Hamed Haddadi

机构 * Imperial College London(伦敦帝国学院) Dartmouth College(达特茅斯学院)

AI总结 WARP通过利用神经网络对称性减少遗忘集梯度能量和参数分散,提升删除学习协议的攻击鲁棒性,有效降低对抗优势。

Comments This work has been accepted for publication at the International Conference on Learning Representations (ICLR) 2026 (to appear)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.02012 2026-03-03 cs.CV cs.AI

MAP-Diff: Multi-Anchor Guided Diffusion for Progressive 3D Whole-Body Low-Dose PET Denoising

MAP-Diff: 多锚点引导的扩散模型用于渐进式三维全身低剂量PET去噪

Peiyuan Jing, Chun-Wun Cheng, Liutao Yang, Zhenxuan Zhang, Thiago V. Lima, Klaus Strobel, Antoine Leimgruber, Angelica Aviles-Rivero, Guang Yang, Javier A. Montoya-Zegarra

机构 * School of Engineering, Zurich University of Applied Sciences, CH Bioengineering Department Imperial-X, Imperial College London, UK DAMTP, University of Cambridge, UK Lucerne University Teaching Research Hospital, CH Lung Institute, Imperial College London, UK Cardiovascular Research Centre, Royal Brompton Hospital, UK School of Biomedical Engineering \& Imaging Sciences, King's College London, UK Yau Mathematical Sciences Center, Tsinghua University, CN

AI总结 MAP-Diff通过多锚点引导的扩散模型实现低剂量PET图像的渐进式去噪,提升PSNR和SSIM,降低NMAE,优于多种基线方法。

Comments 8 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22308 2026-03-03 cs.LG cs.AI cs.CR

Stealthy Poisoning Attacks Bypass Defenses in Regression Settings

隐秘污染攻击在回归设置中绕过防御

Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu

机构 * IBM Research Europe, Portal, First Floor Trinity Business School, Trinity College Dublin(IBM欧洲研究院,波特尔大楼,特里尼蒂商务学校,特里尼蒂学院都柏林) Imperial College London, South Kensington Campus(伦敦帝国理工学院,南肯辛顿校区) Universidad de Alcalá de Henares, Escuela Politécnica Superior(阿尔卡萨大学,工程技术学院) Defence Science and Technology Laboratory (DSTL), Porton Down, Salisbury(国防科学与技术实验室(DSTL),波特恩道,萨里)

AI总结 本文提出了一种隐秘污染攻击的新方法,并开发了BayesClean防御机制,以提升回归模型在面对隐秘攻击时的鲁棒性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.13574 2026-03-03 cs.RO cs.AI

Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation

密集跳跃流匹配与非均匀时间调度在机器人策略中的应用:缓解多步推断退化

Zidong Chen, Zihao Guo, Peng Wang, ThankGod Itua Egbe, Yan Lyu, Chenghao Qian

机构 * Dept. Computing, Imperial College London(帝国理工学院伦敦分校计算机系) Dept. Computing, Manchester Metropolitan University(曼彻斯特 Metropolitan 大学计算机系) CVSSP, University of Surrey(萨里大学CVSSP研究中心) School of Computer Science and Engineering, Southeast University(东南大学计算机科学与工程学院) Institute for Transport Studies, the University of Leeds(利兹大学交通研究所)

AI总结 本文提出了一种利用非均匀时间调度和密集跳跃积分的机器人策略,通过优化训练和推断过程,显著提升了多步骤任务中的性能表现。

详情

展开后加载摘要…

URL PDF HTML 收藏
2404.06230 2026-03-03 cs.LG cs.CR cs.DC

Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated Learning

攻击性或不可察觉,或两者兼有:网络剪枝辅助的混合拜占庭攻击在联邦学习中

Emre Ozfatura, Kerem Ozfatura, Baturalp Buyukates, Mert Coskuner, Alptekin Kupcu, Deniz Gunduz

机构 * Sabancı University(萨班大大学) Koç University(科卡大学) Imperial College London(伦敦帝国学院) University of Birmingham(伯明翰大学)

AI总结 本文提出了一种混合稀疏拜占庭攻击,通过利用神经网络架构的侧信息,设计出既能造成最大破坏又不易被检测的攻击策略。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.01104 2026-03-03 cs.HC cs.AI cs.CV cs.CY

Egocentric Co-Pilot: Web-Native Smart-Glasses Agents for Assistive Egocentric AI

第一人称共驾:面向辅助第一人称AI的网页原生智能眼镜代理

Sicheng Yang, Yukai Huang, Weitong Cai, Shitong Sun, Fengyi Fang, You He, Yiqiao Xie, Jiankang Deng, Hang Zhang, Jifei Song, Zhensong Zhang

机构 * Shenzhen International Graduate School Tsinghua University Shenzhen China(深圳国际研究生院清华大学深圳中国) Independent Researcher London United Kingdom(独立研究者伦敦英国) Queen Mary University of London London United Kingdom(女王玛丽大学伦敦英国) Imperial College London London United Kingdom(帝国理工学院伦敦英国) University Of Surrey Guildford United Kingdom(Surrey大学Guildford英国)

AI总结 Egocentric Co-Pilot通过网页原生智能眼镜代理实现第一人称AI的持续辅助,结合神经符号框架和多模态意图层,展示了在日常生活中提升可及性和情境感知的实用路径。

Comments 14 pages, 6 figures, WWW 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00756 2026-03-03 cs.CV cs.AI

Stroke outcome and evolution prediction from CT brain using a spatiotemporal diffusion autoencoder

基于CT脑部扫描的中风结果与演变预测:时空扩散自编码器

Adam Marcus, Paul Bentley, Daniel Rueckert

机构 * Imperial College London(帝国理工学院伦敦分校) Technische Universität München(慕尼黑技术大学)

AI总结 本文提出一种基于CT图像的时空扩散自编码器,用于预测中风结果与演变,通过自监督学习生成语义表示并结合纵向数据提升预测性能。

Comments Accepted in The 6th International Workshop on Machine Learning in Clinical Neuroimaging (MLCN 2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00289 2026-03-03 cs.CV

Seeking Necessary and Sufficient Information from Multimodal Medical Data

从多模态医学数据中寻求必要和充分的信息

Boyu Chen, Weiye Bao, Junjie Liu, Michael Shen, Bo Peng, Paul Taylor, Zhu Li, Mengyue Yang

机构 * University College London, London, UK(伦敦大学学院) Imperial College London, London, UK(伦敦帝国学院) Mingdu Tech, China(明都科技) University of Bristol, Bristol, UK(布里斯托大学)

AI总结 本文提出通过概率必要性和充分性学习多模态医学数据中的必要和充分特征,以提升模型性能和鲁棒性。

Comments 11 pages, 1 figure. Submitted to MICCAI 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11428 2026-03-03 cs.CV

ImagiDrive: A Unified Imagination-and-Planning Framework for Autonomous Driving

ImagiDrive: 一种用于自动驾驶的统一想象与规划框架

Jingyu Li, Bozhou Zhang, Xin Jin, Jiankang Deng, Xiatian Zhu, Li Zhang

机构 * School of Data Science, Fudan University(复旦大学数据科学学院) Shanghai Innovation Institute(上海创新研究院) Eastern Institute of Technology(技术东院) Imperial College London(伦敦帝国理工学院) University of Surrey(萨里大学)

AI总结 ImagiDrive通过整合视觉-语言模型和驾驶世界模型,实现自动驾驶中的统一想象与规划循环,提升场景生成和决策预测的准确性与效率。

Comments Accepted for publication in 2026 IEEE International Conference on Robotics and Automation (ICRA)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19193 2026-03-03 cs.LG

SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Data

SuperMAN:基于时间稀疏异构数据的可解释且表达性强的网络

Maya Bechler-Speicher, Andrea Zerio, Maor Huri, Marie Vibeke Vestergaard, Ran Gilad-Bachrach, Tine Jess, Samir Bhatt, Aleksejs Sazonovs

机构 * Meta Center of Excellence for Molecular Prediction of IBD (PREDICT)(分子预测IBD中心(PREDICT)) Department of Clinical Medicine, Aalborg University(临床医学系,奥胡斯大学) Department of Gastroenterology & Hepatology, Aalborg University Hospital(消化内科与肝病科,奥胡斯大学医院) University of Copenhagen(哥本哈根大学) Imperial College London(伦敦帝国理工学院) Department of Biomedical Engineering, Tel-Aviv University(生物医学工程系,特拉维夫大学) Sagol School of Neuroscience, Tel-Aviv University(神经科学学院,特拉维夫大学)

AI总结 SuperMAN通过建模时间稀疏异构数据为隐式图集,提供可解释性和表达性,用于医疗诊断和虚假新闻检测等高风险任务。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.00008 2026-03-03 cs.MA cs.AI cs.LO

Strength Change Explanations in Quantitative Argumentation

量化论证中的强度变化解释

Timotheus Kampik, Xiang Yin, Nico Potyka, Francesca Toni

机构 * Umeå University(乌梅拉大学) Imperial College London(伦敦帝国学院) Cardiff University(卡迪夫大学)

AI总结 本文提出强度变化解释方法,用于在定量论证图中实现期望推理结果,通过调整论证强度来达成目标排序,并探讨其正确性与应用限制。

Comments This is an AAMAS '26 paper, with additional supplementary material

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.24183 2026-03-02 cs.CV cs.LG

A multimodal slice discovery framework for systematic failure detection and explanation in medical image classification

一种用于医学图像分类中系统性故障检测和解释的多模态切片发现框架

Yixuan Liu, Kanwal K. Bhatia, Ahmed E. Fetit

机构 * Department of Computing, Imperial College London, UK(帝国理工学院 computing 部,英国) Aival, London, UK(Aival,伦敦,英国)

AI总结 该研究提出了一种多模态切片发现框架,用于医学图像分类中的系统性故障检测与解释,展示了其在故障发现和解释生成方面的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.24172 2026-03-02 cs.CL cs.AI

ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models

ArgLLM-App:基于大语言模型的论证推理交互系统

Adam Dejl, Deniz Gorur, Francesca Toni

机构 * Imperial College London(伦敦帝国学院)

AI总结 ArgLLM-App是一个基于大语言模型的论证推理交互系统,通过可视化解释和用户交互实现决策的可解释性和可挑战性。

Comments AAMAS 2026 Demonstration Track

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.04855 2026-03-02 cs.LG

Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders

通过标签条件高斯混合变分自编码器合成反事实解释

Junqi Jiang, Francesco Leofante, Antonio Rago, Francesca Toni

机构 * Imperial College London(帝国理工学院伦敦分校) J.P. Morgan AI Research(摩根大通人工智能研究) King’s College London(伦敦国王学院)

AI总结 LAPACE通过标签条件高斯混合变分自编码器生成稳健且多样化的反事实解释路径,实现高效且模型无关的CE合成。

Comments Accepted at ICLR 2026. Camera-ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.22402 2026-02-27 cs.SE cs.AI cs.HC cs.OS

Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents

上下文记忆虚拟化:基于DAG的状态管理和结构无损修剪用于LLM代理

Cosmo Santoni

机构 * Imperial College London(伦敦帝国学院)

AI总结 上下文记忆虚拟化通过DAG结构管理和无损修剪技术,提升LLM代理在长期推理任务中的上下文重用效率和经济性。

Comments 11 pages. 6 figures. Introduces a DAG-based state management system for LLM agents. Evaluation on 76 coding sessions shows up to 86% token reduction (mean 20%) while remaining economically viable under prompt caching. Includes reference implementation for Claude Code

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24266 2026-02-27 cs.RO cs.HC

SignBot: Learning Human-to-Humanoid Sign Language Interaction

SignBot: 学习人类-人形机器人手语交互

Guanren Qiao, Sixu Lin, Ronglai Zuo, Zhizheng Wu, Kui Jia, Guiliang Liu

机构 * School of Data Science, the Chinese University of Hong Kong, Shenzhen(数据科学学院,香港中文大学(深圳)) Imperial College London(伦敦帝国理工学院)

AI总结 SignBot通过整合运动重定向、运动控制和生成交互模块,实现人与人形机器人之间自然的手语交流,提升聋人和听力障碍者的沟通可及性。

Comments Accepted by ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21735 2026-02-26 cs.CV

SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning

SigVLP:基于sigmoid体积-语言预训练的自监督CT体积自适应表示学习

Jiayi Wang, Hadrien Reynaud, Ibrahim Ethem Hamamci, Sezgin Er, Suprosanna Shit, Bjoern Menze, Bernhard Kainz

机构 * Friedrich-Alexander University Erlangen-Nürnberg(弗里德里希-亚历山大大学埃尔兰根-纽伦堡) Department of Quantitative Biomedicine, University of Zurich(苏黎世大学定量生物医学系) ETH AI Center, ETH Zurich(苏黎世联邦理工学院AI中心) International School of Medicine, Istanbul Medipol University(伊斯坦布尔梅迪波尔大学国际医学院) Department of Computing, Imperial College London(伦敦帝国学院计算机系)

AI总结 SigVLP通过引入旋转位置嵌入和块级对齐方法,改进CT体积与文本的自监督表示学习,提升文本到体积对齐的精度。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.11910 2026-02-26 cs.CV

Seeing the Forest and the Trees: Query-Aware Tokenizer for Long-Video Multimodal Language Models

看清森林与树木:面向长视频多模态语言模型的查询感知分词器

Siyou Li, Huanan Wu, Juexi Shao, Yinghao Ma, Yujian Gan, Yihao Luo, Yuwei Wang, Dong Nie, Lu Wang, Wenqing Wu, Le Zhang, Massimo Poesio, Juntao Yu

机构 * Queen Mary University of London(伦敦女王学院) University of Sheffield(谢菲尔德大学) Imperial College London(伦敦帝国学院) Pengcheng Laboratory(鹏城实验室) Meta Inc(Meta公司) Meituan Inc(美团公司) Nanjing University of Science(南京理工大学) University of Birmingham(伯明翰大学) Utrecht University(乌得勒支大学)

AI总结 QTSplus是一种轻量高效的视觉token选择模块,通过动态选择重要视觉证据提升长视频多模态语言模型的性能,显著降低计算成本并提高处理效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21622 2026-02-26 cs.RO

ADM-DP: Adaptive Dynamic Modality Diffusion Policy through Vision-Tactile-Graph Fusion for Multi-Agent Manipulation

ADM-DP: 通过视觉-触觉-图融合的自适应动态模态扩散策略用于多智能体操作

Enyi Wang, Wen Fan, Dandan Zhang

机构 * Department of Bioengineering, Imperial-X Initiative, Imperial College London(生物工程系、Imperial-X计划、帝国理工学院伦敦分校)

AI总结 ADM-DP通过视觉-触觉-图融合的自适应动态模态扩散策略,提升多智能体操作的协调性、抓取稳定性和碰撞避免性能。

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.21143 2026-02-25 cs.AI cs.CL cs.IR cs.LG

A Benchmark for Deep Information Synthesis

深度信息合成的基准测试

Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov, Lena Sophia Bolliger, Aysim Toker, Roy Miles, Andreea-Maria Oncescu, Jasivan Alex Sivakumar, Philipp Borchert, Ismail Elezi, Meiru Zhang, Ka Yiu Lee, Guchun Zhang, Jun Wang, Gerasimos Lampouras

机构 * Huawei Noah’s Ark Lab, UK(华为诺亚实验室,英国) Imperial College London(伦敦帝国理工学院) UCL Centre for Artificial Intelligence(伦敦大学学院人工智能中心) University of Zurich(苏黎世大学) University of Sheffield(谢菲尔德大学) University of Cambridge(剑桥大学)

AI总结 DEEPSYNTH是一个评估智能体在复杂任务中信息合成与推理能力的新基准测试,通过多阶段数据收集流程和120个跨7个领域的任务,评估LLM在现实问题中的表现。

Comments Accepted at ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20159 2026-02-25 cs.CV cs.AI cs.LG cs.MM cs.RO

A Very Big Video Reasoning Suite

一个非常大的视频推理套件

Maijunxian Wang, Ruisi Wang, Juyi Lin, Ran Ji, Thaddäus Wiedemer, Qingying Gao, Dezhi Luo, Yaoyao Qian, Lianyu Huang, Zelong Hong, Jiahui Ge, Qianli Ma, Hang He, Yifan Zhou, Lingzi Guo, Lantao Mei, Jiachen Li, Hanwen Xing, Tianqi Zhao, Fengyuan Yu, Weihang Xiao, Yizheng Jiao, Jianheng Hou, Danyang Zhang, Pengcheng Xu, Boyang Zhong, Zehong Zhao, Gaoyun Fang, John Kitaoka, Yile Xu, Hua Xu, Kenton Blacutt, Tin Nguyen, Siyuan Song, Haoran Sun, Shaoyue Wen, Linyang He, Runming Wang, Yanzhi Wang, Mengyue Yang, Ziqiao Ma, Raphaël Millière, Freda Shi, Nuno Vasconcelos, Daniel Khashabi, Alan Yuille, Yilun Du, Ziming Liu, Bo Li, Dahua Lin, Ziwei Liu, Vikash Kumar, Yijiang Li, Lei Yang, Zhongang Cai, Hokin Deng

机构 * University of California, Berkeley(加州大学伯克利分校) Nanyang Technological University(南洋理工大学) Northeastern University(东北大学) University of Tübingen(图宾根大学) Johns Hopkins University(约翰霍普金斯大学) University of Michigan(密歇根大学) University of Southern California(南加州大学) Washington University in St. Louis(圣路易斯华盛顿大学) Shanghai Jiao Tong University(上海交通大学) East China Normal University(华东师范大学) Stanford University(斯坦福大学) University of Texas at Austin(得克萨斯大学奥斯汀分校) University of California, Los Angeles(加州大学洛杉矶分校) Cornell University(康奈尔大学) San Jose State University(圣何塞州立大学) University of California, Irvine(加州大学尔湾分校) Technical University of Munich(慕尼黑技术大学) University of California, San Diego(加州大学圣地亚哥分校) Imperial College London(伦敦帝国学院) University of Wisconsin--Madison(威斯康星大学麦迪逊分校) University of Edinburgh(爱丁堡大学) Hong Kong University of Science(香港科学大学) New York University(纽约大学) Auburn University(阿伯丁大学) Columbia University(哥伦比亚大学) University of Bristol(布里斯托大学) University of Waterloo(滑铁卢大学) The Chinese University of Hong Kong(香港中文大学) Carnegie Mellon University(卡内基梅隆大学) University of Oxford(牛津大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校)

AI总结 VBVR数据集和评估框架旨在解决视频推理能力研究中的大规模数据缺乏问题,通过大规模实验观察到对未见任务的泛化能力。

Comments Homepage: https://video-reason.com/

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20628 2026-02-25 cs.AI

When can we trust untrusted monitoring? A safety case sketch across collusion strategies

我们何时可以信任不可信的监控?跨合谋策略的安全案例草图

Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin

机构 * LASR Labs(LASR实验室) University of Oxford(牛津大学) University of Wyoming(怀俄明大学) Imperial College London(伦敦帝国学院) UK AI Security Institute(英国人工智能安全研究所)

AI总结 本文提出了一种跨合谋策略的安全案例草图,探讨了不可信监控的安全性问题,分析了不同合谋策略的有效性,并指出了未解决的挑战。

Comments 66 pages, 14 figures, Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.20557 2026-02-25 cs.LG cs.SC

GENSR: Symbolic Regression Based in Equation Generative Space

GENSR:基于方程生成空间的符号回归

Qian Li, Yuxiao Hu, Juncheng Liu, Yuntian Chen

机构 * Shanghai Jiao Tong University(上海交通大学) Eastern Institute of Technology(东部技术研究所) The Hong Kong Polytechnic University(香港理工大学) Imperial College London(伦敦帝国理工学院)

AI总结 GenSR通过生成潜在空间和改进的CMA-ES算法,实现了符号回归中预测准确性、表达简洁性和计算效率的联合优化。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.06868 2026-02-25 cs.IT cs.AI cs.CR cs.LG math.IT

Multi-hop Deep Joint Source-Channel Coding with Deep Hash Distillation for Semantically Aligned Image Recovery

多跳深度联合源信道编码与深度哈希蒸馏用于语义对齐的图像恢复

Didrik Bergström, Deniz Gündüz, Onur Günlü

机构 * Department of Electrical and Electronic Engineering, Imperial College London, UK(电气与电子工程系,帝国理工学院伦敦分校,英国) Lehrstuhl für Nachrichtentechnik, Technische Universität Dortmund, Germany(信息论系,德意志理工大学多特蒙德分校,德国)

AI总结 本文提出多跳深度联合源信道编码结合深度哈希蒸馏,以提升图像恢复的语义一致性与感知质量。

Comments Change last word in title, add missing trailing bracket, add additional simulation results in section 4.1; results unchanged

详情

展开后加载摘要…

URL PDF HTML 收藏