arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Toronto(多伦多大学)

共收录 126
2604.02330 2026-08-03 cs.CV cs.AI cs.LG 版本更新

ActionParty: Multi-Subject Action Binding in Generative Video Games

ActionParty:生成视频游戏中的多主体动作绑定

Alexander Pondaven, Ziyi Wu, Igor Gilitschenski, Philip Torr, Sergey Tulyakov, Fabio Pizzati, Aliaksandr Siarohin

机构 * Snap Research(Snap研究院) University of Oxford(牛津大学) University of Toronto(多伦多大学) MBZUAI(穆罕默德·本·扎耶德人工智能大学)

AI总结 本文提出ActionParty,一种可控制多主体的生成视频游戏世界模型,通过引入主体状态标记和空间偏置机制,提升动作关联准确性与身份一致性。

Comments ECCV 2026 - Project page: https://action-party.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22146 2026-08-03 cs.CL cs.LG 版本更新

FineInstructions: Scaling Synthetic Instructions to Pre-Training Scale

精细指令:将合成指令扩展到预训练规模

Ajay Patel, Colin Raffel, Chris Callison-Burch

机构 * University of Pennsylvania(宾夕法尼亚大学) University of Toronto(多伦多大学) Vector Institute(向量研究所)

AI总结 研究针对大语言模型监督训练数据有限的问题,提出将互联网规模预训练文档知识转化为合成指令和答案训练对的程序,生成FineInstructions数据集,经实验验证该方法在预训练中表现优于其他技术。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.26991 2026-07-31 cs.RO 版本更新

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

RL²-VLA:面向视觉-语言-动作模型的测试时缩放自适应RL隐成分引导

Derek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer, William Wei Jie Teo, Yuanliang Ju, Qiao Gu, Guillaume Sartoretti

机构 * National University of Singapore(新加坡国立大学) University of Toronto(多伦多大学) Singapore Technologies Engineering(新加坡科技工程公司)

AI总结 针对VLA模型分布外任务性能下降问题,提出基于VLA隐空间的自适应推理时引导框架RL²,仅在预测失败时激活成分引导,在SIMPLER等基准上分布外成功率最高提升17.3%,可迁移至真实世界。

Comments Code and models are available at https://rl2-vla.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.22078 2026-07-31 cs.RO 版本更新

Do World Action Models Generalize Better than VLAs? A Robustness Study

世界动作模型是否比视觉语言动作模型表现更好?一项鲁棒性研究

Zhanguang Zhang, Zhiyuan Li, Behnam Rahmati, Rui Heng Yang, Yintao Ma, Amir Rasouli, Sajjad Pakdamansavoji, Yangzheng Wu, Lingfeng Zhang, Tongtong Cao, Feng Wen, Xinyu Wang, Xingyue Quan, Yingxue Zhang

机构 * Huawei Technologies(华为技术有限公司) University of Toronto(多伦多大学)

AI总结 本文比较了最新状态的VLA策略和最近发布的WAMs,在不同视觉和语言扰动下评估其性能,发现WAMs在鲁棒性上表现更强,而VLA需要大量训练数据和多样化学习目标。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.01153 2026-07-30 cs.CL cs.AI cs.SE 版本更新

Adversarial Pragmatics for AI Safety Evaluation: A Diagnostic Framework and Seed Benchmark for Language-Mediated Control

面向AI安全评估的对抗语用学:指令冲突、嵌入命令与策略模糊性基准

Brett Reynolds

机构 * Humber Polytechnic(汉博理工学院) University of Toronto(多伦多大学)

AI总结 提出对抗语用学基准和标注协议,通过语言学控制的分类法评估模型在指令冲突、嵌入命令等场景下的行为,为安全评估提供实证和方法论工具。

Comments 32-page main paper plus 13-page supplement; 6 figures and 17 tables total; code and data artifact available at the linked repository

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.18060 2026-07-29 cs.RO 版本更新

RoboHarness: Memory-Driven Orchestration of Heterogeneous Robot Policies for Long-Horizon Planning

RoboHarness:用于长期规划的异构机器人策略的内存驱动编排

Jinbang Huang, Yuanzhao Hu, Zhiyuan Li, Ran Qi, Yixin Xiao, Zhanguang Zhang, Mark Coates, Tongtong Cao, Yingxue Zhang

机构 * Huawei Noah’s Ark Lab(华为诺亚方舟实验室) University of British Columbia(英属哥伦比亚大学) University of Toronto(多伦多大学) McGill University(麦吉尔大学) Labs(2012实验室)

AI总结 针对长期机器人任务需多种能力、异构策略编排难的问题,提出RoboHarness框架,通过多模态执行内存等表征策略能力边界,经内存桥接稳定策略交接,实验验证其在长期规划和分布外鲁棒性上有显著提升。

Comments 21 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03881 2026-07-29 cs.CY cs.AI cs.HC 版本更新

LLM-generated personalized nudges for improving pro-environmental behavior: Field evidence from resource conservation

利用大型语言模型的迭代个性化增强行为提示:一项关于电力和热水节约的实地实验

Zonghan Li, Yi Liu, Chunyan Wang, Song Tong, Kaiping Peng, Feng Ji

机构 * School of Environment, Tsinghua University(清华大学环境学院) Department of Applied Psychology and Human Development, University of Toronto(多伦多大学应用心理学与人类发展系) State Key Laboratory of Regional Environment and Sustainability, Tsinghua University(清华大学区域环境与可持续性国家重点实验室) Department of Psychology, Beijing Normal University at Zhuhai(北京师范大学珠海校区心理学系) Department of Psychology and Cognitive Sciences, Tsinghua University(清华大学心理学与认知科学系)

AI总结 本研究利用大型语言模型实现迭代个性化,通过实地实验发现其在促进节能方面效果显著,且在前两轮干预中表现更优,但热水节约效果较弱且随时间减弱。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.20662 2026-07-28 cs.RO cond-mat.mtrl-sci 版本更新

Scalable Low-Cost Laboratory Automation: A Digital Twin-Integrated Robotic Platform for Autonomous Liquid Handling (RAINBOT)

可扩展的低成本实验室自动化:用于自主液体处理的数字孪生集成机器人平台(RAINBOTTM)

Mohamed Rami Ayeche, Souhil Sid, Ahyen Mostofa, Rehaan Hussain, Ali Shayesteh, Fadwa El Mellouhi

机构 * Acceleration Consortium, University of Toronto(多伦多大学加速联盟) AISCIA Informatics(AISCIA信息学公司) Hamad Bin Khalifa University (HBKU)(哈马德·本·哈利法大学)

AI总结 研究针对商业液体处理系统的局限,提出将消费级3D打印机改装为低成本液体处理机器人RAINBOTTM的方法,通过数字孪生实现远程监控,结合CEIDTM框架进行目标导向实验,成本低,建立了可访问的物理 - 虚拟实验室自动化框架。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.08728 2026-07-28 cs.AI cs.CL cs.CV cs.LG 版本更新

Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery

人工智能数学推理:语言模型、神经符号系统与验证发现的综合综述

Syed Rifat Raiyan, Mohsinul Kabir, Hasan Mahmud, Md Kamrul Hasan, Sophia Ananiadou

机构 * University of California, Berkeley(加州大学伯克利分校) University of Cambridge(剑桥大学) University of Toronto(多伦多大学)

AI总结 本文综述了数学推理领域从早期规则系统到当代推理模型、多智能体系统及验证发现工作流的演变,沿非正式推理、形式推理、数学发现及推理技术四轴组织,并评估了基准测试、失败模式及未来方向。

Comments Under review, 47 pages, 14 figures, 22 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.15357 2026-07-28 cs.CV cs.LG 版本更新

MaskAttn-SDXL: Controllable Region-Level Text-To-Image Generation

MaskAttn-SDXL:可控区域级文本到图像生成

Yu Chang, Jiahao Chen, Anzhe Cheng, Paul Bogdan

机构 * University of Southern California(南加州大学) University of Toronto(多伦多大学)

AI总结 本文提出MaskAttn-SDXL模块,通过在softmax前注入token条件空间门控,解决扩散模型在多物体生成中的全局协调和可靠性问题,无需改变SDXL流程。

Comments Published in the 2026 International Joint Conference on Neural Networks (IJCNN 2026)

Journal ref Proceedings of the 2026 International Joint Conference on Neural Networks (IJCNN 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.02458 2026-07-28 cs.CY cs.AI cs.ET 版本更新

Statistical realism is not evidence that LLMs can estimate treatment effects in social science experiments

当模拟看起来正确但因果效应出错:大型语言模型作为行为模拟器

Zonghan Li, Feng Ji

机构 * University of Toronto(多伦多大学)

AI总结 研究评估了大型语言模型在气候心理学干预中的行为模拟能力,发现描述性拟合不等于因果准确性,不同干预逻辑和结果类型导致误差差异,提示依赖描述性拟合可能误导干预效果结论。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.28963 2026-07-28 cs.RO cs.AI cs.CV cs.LG 版本更新

AutoWorld: Learning Multi-Agent Traffic Simulation with Self-Supervised World Models

AutoWorld: 通过自监督世界模型扩展多智能体交通仿真

Mozhgan Pourkeshavarz, Tianran Liu, Nicholas Rhinehart

机构 * University of Toronto(多伦多大学)

AI总结 本文提出AutoWorld框架,利用未标记的LiDAR数据自监督学习世界模型,提升多智能体交通仿真的真实感与性能,实验表明未标记数据能有效提升仿真效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.04260 2026-07-28 cs.HC cs.AI 版本更新

Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering

可控聊天机器人:通过大语言模型激活引导探索个性化控制界面

Jessica Y. Bo, Tianyu Xu, Ishan Chatterjee, Katrina Passarella-Ward, Achin Kulshrestha, D Shin

机构 * University of Toronto(多伦多大学) Google AR(谷歌AR)

AI总结 研究探索可控聊天机器人范式,通过激活引导实现个性化,利用线性标量控制偏好表达强度,设计三种界面原型并进行用户研究,发现其在冷启动任务中比单独提示更能契合用户偏好,揭示了相关个性化方面的不同价值。

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.19212 2026-07-27 cs.CL cs.AI cs.CY 版本更新

When Ethics and Payoffs Diverge: LLM Agents in Morally Charged Social Dilemmas

当伦理与收益相悖时:道德两难情境下的大语言模型智能体

Steffen Backmann, David Guzman Piedrahita, Terry Jingchen Zhang, Emanuel Tewolde, Rada Mihalcea, Bernhard Schölkopf, Zhijing Jin

机构 * ETH Zürich(苏黎世联邦理工学院) University of Zurich(苏黎世大学) Carnegie Mellon University(卡内基梅隆大学) University of Michigan(密歇根大学) Max Planck Institute for Intelligent Systems, Tübingen(图宾根人工智能研究所) University of Toronto(多伦多大学) Vector Institute(向量研究所)

AI总结 研究道德要求与利润激励冲突时LLMs在道德两难博弈中的行为,引入\msim评估九个模型,通过ATEs估计因果效应、分析推理轨迹,发现模型道德行为有情境脆弱性,揭示了部署风险。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.14575 2026-07-23 cs.LG cs.AI stat.ME stat.ML 版本更新

Generative Augmented Inference of LLM-generated Data for Market Research: Theory and Empirical Evidence

生成式增强推断

Cheng Lu, Mengxin Wang, Dennis J. Zhang, Heng Zhang

机构 * University of California, Berkeley(加州大学伯克利分校) Stanford University(斯坦福大学) University of Toronto(多伦多大学)

AI总结 提出生成式增强推断(GAI)框架,将AI输出视为学习真实标签的高维信息特征而非代理,通过非参数方法建模,实现人机数据联合的一致估计和有效推断,在随机标注下渐近效率严格优于仅用人类数据。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.12037 2026-07-23 cs.LG 版本更新

Frequentist Consistency of Prior-Data Fitted Networks for Causal Inference

用于因果推断的先验数据拟合网络的频率派一致性

Valentyn Melnychuk, Vahid Balazadeh, Stefan Feuerriegel, Rahul G. Krishnan

机构 * LMU Munich \& Munich Center for Machine Learning (MCML), Munich, Germany University of Toronto \& Vector Institute, Toronto, Canada

AI总结 本文分析基于先验数据拟合网络(PFN)的平均处理效应(ATE)估计量的频率派一致性,发现其存在先验诱导的混淆偏差,并提出基于一步后验校正(OSPC)的校准方法,结合鞅后验恢复功能干扰后验,从而恢复频率派一致性并实现半参数Bernstein-von Mises定理。

Journal ref Proceedings of the 43-rd International Conference on Machine Learning, Seoul, South Korea, PMLR 306, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.26408 2026-07-22 cs.RO 版本更新

Exploring the Intrinsic Geometry of Diffusion Models with Constrained Inverse Kinematics

探索扩散模型在约束逆运动学中的内在几何结构

Miguel Angel Rogel Garcia, Phone Thiha Kyaw, Jonathan Kelly

机构 * Institute for Aerospace Studies, University of Toronto(航空航天研究所以及多伦多大学)

AI总结 通过约束逆运动学问题,研究扩散模型能否恢复数据流形的内在几何结构,实验表明模型得分函数恢复的内在维度与解析自由度匹配,且潜在空间线性插值保持约束流形结构。

Comments In Proceedings of the Robotics: Science and Systems (RSS) 2026 Workshop on Diffusion for Robot Learning, Sydney, Australia, July 17, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.08571 2026-07-22 cs.LG cs.AI cs.CL 版本更新

Robust Reasoning Benchmark

鲁棒推理基准

Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey

机构 * University of Toronto(多伦多大学) Vector Institute(向量研究所)

AI总结 本研究提出鲁棒推理基准(RRB),通过13种确定性文本扰动评估8种前沿模型,发现Claude在面对变换提示时表现出异常拒绝行为,而开放权重模型在结构噪声下出现多种失败模式,如认知冲刷、分词崩溃和推理崩溃,导致平均准确率下降高达54%。研究进一步发现由模型自身推理链引起的注意力稀释问题,并提出Intra-Query Attention Dilution概念,表明中间推理步骤会污染标准密集注意力机制,未来架构需整合显式上下文重置以实现可靠推理。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.21014 2026-07-22 cs.LG cs.CL 版本更新

CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs

CLT-Forge:一种可扩展的跨层转码器和归因图库

Florent Draye, Vedant Palit, Abir Harrasse, Tung-Yu Wu, Jiarui Liu, Punya Syon Pandey, Roderick Wu, Chih-Hao Hsu, Terry Jingchen Zhang, Zhijing Jin, Bernhard Schölkopf

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) Jinesis AI Lab(Jinesis人工智能实验室) University of Toronto(多伦多大学) Vector Institute(向量研究所) CMU(卡内基梅隆大学) EuroSafeAI ELLIS Institute Tübingen(图宾根ELLIS研究所)

AI总结 本文提出CLT-Forge库,通过分布式训练、模型分片和压缩激活缓存提升跨层转码器的可扩展性,提供统一的可解释性流程和可视化接口,解决归因图的冗余问题。

Comments 9 pages, 7 figures, 1 table. Code: https://github.com/LLM-Interp/CLT-Forge. Demonstration video: https://youtu.be/6ptrrLawTl8

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.04843 2026-07-22 cs.AI 版本更新

Fluid Reasoning Representations

推理模型中的流体表示

Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin

机构 * ETH Zurich(苏黎世联邦理工学院) University of Toronto(多伦多大学)

AI总结 研究揭示了推理模型通过上下文细化令牌表示提升抽象问题解决能力的机制,提出流体推理表示概念。

Comments EMNLP 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.16727 2026-07-22 cs.CV cs.LG 版本更新

Pain in 3D: Generating Controllable Synthetic Faces for Automated Pain Assessment

3D 中的疼痛:生成用于自动疼痛评估的可控合成面部

Xin Lei Lin, Soroush Mehraban, Abhishek Moturu, Babak Taati

机构 * Vector Institute(向量研究所) KITE Research Institute(KITE研究机构) University Health Network(大学健康网络) Department of Computer Science, University of Toronto(多伦多大学计算机科学系) Department of Medical Imaging, University of Toronto(多伦多大学医学成像系) Institute of Biomedical Engineering, University of Toronto(多伦多大学生物医学工程研究所)

AI总结 研究针对面部表情自动疼痛评估面临的数据稀缺等问题,提出3DPain数据集及三阶段框架合成多视图面部,还引入ViTPain框架,为可推广的自动疼痛评估建立了可控、多样且基于临床的基础。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15407 2026-07-20 math.NA cs.AI cs.NA 版本更新

Energy-based Transport for Amortized Bayesian Inference

平均能量基于的贝叶斯推断

Ricardo Baptista, Hojjat Kaveh, Andrew M. Stuart

机构 * California Institute of Technology(加州理工学院) University of Toronto(多伦多大学)

AI总结 本文研究了在仅能获取参数和观测联合分布样本的情况下,非线性逆问题的平均能量基于的贝叶斯推断方法,提出了一种基于传输的方法,通过学习观测依赖的映射来近似后验分布,避免了传统方法的计算开销。

Comments 25 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.03747 2026-07-17 cs.RO 版本更新

Observability-Aware Control for Quadrotor Formation Flight with Range-only Measurement

具有仅距离测量的四旋翼编队飞行的可观测性意识控制

H S Helson Go, Ching Lok Chong, Longhao Qian, Hugh H. -T. Liu

机构 * Institute for Aerospace Studies, University of Toronto(多伦多大学航空航天研究 institute)

AI总结 本文提出一种基于STLOG的OPC控制器,用于提升四旋翼编队飞行在仅距离测量下的可观测性与定位鲁棒性。

Comments 37 pages, 5 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.08016 2026-07-16 cs.CV cs.GR 版本更新

LightCrafter: PBR-Conditioned Video Diffusion Refinement for Controllable and Consistent Relighting

LightCrafter:用于可控且一致的重光照的PBR条件视频扩散细化

Zixin Guo, Yehonathan Litman, Yifeng He, John Miller, Chuhan Chen, Deva Ramanan

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Toronto(多伦多大学) Bosch Research(博世研究)

AI总结 研究视频重光照问题,提出LightCrafter混合管道,将其重表述为代理视频转换,利用PBR渲染并结合光度先验,在真实世界重光照基准上优于现有技术,还贡献合成基准及相关资源。

Comments Project page: https://www.zixinguo.me/lightcrafter

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.01531 2026-07-16 cs.AI cs.LG 版本更新

OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3

OPINE-World:基于本体错误优先的交互式探索的程序化世界建模

David Courtis, Wenhao Li, Scott Sanner

机构 * University of Toronto(多伦多大学)

AI总结 提出OPINE-World,一种在线交互学习面向对象的程序化世界模型的LLM智能体,通过本体错误度量引导探索,在ARC-AGI-3基准上无需逐游戏训练即解决20/25个游戏,动作效率达78.4。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.27201 2026-07-15 cs.LG 版本更新

Explaining Temporal Graph Neural Networks via Feature-induced Information Flow

解释时序图神经网络通过特征诱导的信息流

Ping Xiong, Thomas Schnake, Klaus-Robert Müller, Shinichi Nakajima

机构 * Berlin Institute for the Foundations of Learning and Data – BIFOLD(柏林学习与数据基础研究所) Machine Learning Group, Technical University of Berlin(柏林工业大学机器学习组) RIKEN AIP(日本理化学研究所革新智能综合研究中心) Department of Artificial Intelligence, Korea University(高丽大学人工智能系) Max Planck Institute for Informatics(马克斯·普朗克信息学研究所) Department of Chemistry, Chemical Physics Theory Group, University of Toronto(多伦多大学化学系化学物理理论组) Vector Institute for Artificial Intelligence(向量人工智能研究所) Acceleration Consortium, University of Toronto(多伦多大学加速联盟)

AI总结 提出一种基于归一化相关度量框架的归因方法,通过分析所有事件相关变量的信息流来完整解释事件时序图神经网络,优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09008 2026-07-15 cs.CL cs.AI cs.LG cs.LO 版本更新

A Neurosymbolic Approach to Natural Language Formalization and Verification

一种用于自然语言形式化和验证的神经符号方法

Chenyang An, Sam Bayless, Stefano Buliani, Darion Cassel, Byron Cook, Duncan Clough, Rémi Delmas, Nafi Diallo, Ferhat Erata, Nick Feng, Dimitra Giannakopoulou, Aman Goel, Aditya Gokhale, Joe Hendrix, Victor Heorhiadi, Marc Hudak, Dejan Jovanović, Andrew M. Kent, Benjamin Kiesl-Reiter, Jeffrey J. Kuna, Nadia Labai, Joseph Lilien, Divya Raghunathan, Zvonimir Rakamarić, Niloofar Razavi, Michael Tautschnig, Ali Torkamani, Nathaniel Weir, Michael W. Whalen, Jianan Yao

机构 * Amazon Web Services(亚马逊网络服务) University College London(伦敦大学学院) University of Toronto(多伦多大学) Queen Mary University of London(伦敦大学女王学院)

AI总结 针对大型语言模型缺乏形式正确性保证的问题,提出神经符号方法ARc,通过使用带人工指导的大型语言模型形式化自然语言政策,并在推理时验证逻辑正确性,实现高健全性和低误报率,还能产生可审计工件。

Comments 28 pages, 11 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.17670 2026-07-15 cs.CV cs.LG q-bio.QM q-bio.TO 版本更新

The TopCoW Challenge -- Topology-Aware Circle of Willis Segmentation for CT and MR Angiography

TopCoW挑战——用于CT和MR血管造影的拓扑感知Willis环分割

Kaiyuan Yang, Fabio Musio, Yihui Ma, Norman Juchler, Johannes C. Paetzold, Rami Al-Maskari, Luciano Höher, Hongwei Bran Li, Ibrahim Ethem Hamamci, Anjany Sekuboyina, Suprosanna Shit, Houjing Huang, Chinmay Prabhakar, Ezequiel de la Rosa, Bastian Wittmann, Diana Waldmannstetter, Florian Kofler, Fernando Navarro, Martin J. Menten, Ivan Ezhov, Daniel Rueckert, Iris N. Vos, Ynte M. Ruigrok, Birgitta K. Velthuis, Hugo J. Kuijf, Pengcheng Shi, Wei Liu, Ting Ma, Maximilian R. Rokuss, Yannick Kirchhoff, Fabian Isensee, Klaus Maier-Hein, Chengcheng Zhu, Huilin Zhao, Philippe Bijlenga, Julien Hämmerli, Catherine Wurster, Laura Westphal, Jeroen Bisschop, Elisa Colombo, Hakim Baazaoui, Hannah-Lea Handelsmann, Andrew Makmur, James Hallinan, Amrish Soundararajan, Benedikt Wiestler, Jan S. Kirschke, Evamaria O. Riedel, Roland Wiest, Emmanuel Montagnon, Laurent Letourneau-Guillon, Kwanseok Oh, Dahye Lee, Orhun Utku Aydin, Adam Hilbert, Jana Rieger, Dimitrios Rallios, Satoru Tanioka, Alexander Koch, Dietmar Frey, Abdul Qayyum, Moona Mazher, Steven Niederer, Nico Disch, Julius C. Holzschuh, Dominic LaBella, Francesco Galati, Daniele Falcetta, Maria A. Zuluaga, Chaolong Lin, Haoran Zhao, Zehan Zhang, Minghui Zhang, Xin You, Hanxiao Zhang, Guang-Zhong Yang, Yun Gu, Sinyoung Ra, Jongyun Hwang, Hyunjin Park, Junqiang Chen, Marek Wodzinski, Henning Müller, Nesrin Mansouri, Florent Autrusseau, Cansu Yalcin, Rachika E. Hamadache, Clara Lisazo, Joaquim Salvi, Adrià Casamitjana, Xavier Lladó, Uma Maria Lal-Trehan Estrada, Valeriia Abramova, Luca Giancardo, Arnau Oliver, Paula Casademunt, Adrian Galdran, Matteo Delucchi, Oscar Camara, Jialu Liu, Haibin Huang, Yue Cui, Zehang Lin, Yusheng Liu, Shunzhi Zhu, Tatsat R. Patel, Adnan H. Siddiqui, Vincent M. Tutino, Maysam Orouskhani, Huayu Wang, Mahmud Mossa-Basha, Yuki Sato, Sven Hirsch, Susanne Wegener, Bjoern Menze

机构 * Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland Institute of Computational Life Sciences, Zurich University of Applied Sciences (ZHAW), Waedenswil, Switzerland Department of Neuroradiology, University Hospital of Zurich, Zurich, Switzerland Department of Neurosurgery, Zhongnan Hospital of Wuhan University, Wuhan, China Department of Radiology at Weill Cornell Medicine, Cornell University, New York, USA Institute for Tissue Engineering School of Computation, Information Technology, Technical University of Munich, Germany Athinoula A. Martinos Center for Biomedical Imaging, Harvard Medical School, Boston, USA School of Medicine Health, TUM Klinikum, Technical University of Munich, Germany Munich Center for Machine Learning, Munich, Germany Department of Computing, Imperial College London, London, UK Image Sciences Institute, UMC Utrecht, Utrecht, The Netherlands Department of Neurology Neurosurgery, University Medical Center Utrecht, Utrecht, The Netherlands Department of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands Electronic \& Information Engineering School, Harbin Institute of Technology (Shenzhen), China Peng Cheng Laboratory, Shenzhen, China Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany Faculty of Mathematics Computer Science, Heidelberg University, Germany Helmholtz Imaging, German Cancer Research Center, Heidelberg, Germany Data Science School for Health, Karlsruhe/Heidelberg, Germany Learning Group, Department of Radiation Oncology, Heidelberg University Hospital Department of Radiology, University of Washington, Seattle, WA, USA Department of Radiology, Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China Department of Clinical Neurosciences, Division of Neurosurgery, Geneva University Hospitals, Geneva, Switzerland Department of Neurology, University Hospital of Zurich, Zurich, Switzerland Department of Physiology, University of Toronto, Canada Department of Neurosurgery, University Hospital of Zurich, Zurich, Switzerland Department of Diagnostic Imaging, National University Hospital, Singapore University of Chicago, USA Department of Diagnostic Interventional Neuroradiology, University Hospital Berne University of Berne, Berne, Switzerland Centre de Recherche du Centre Hospitalier de l’Université de Montréal (CRCHUM), Montréal, Québec, Canada DEEPNOID Inc., Seoul, South Korea Department of Artificial Intelligence, Korea University, Seoul, South Korea Charité Lab for AI in Medicine (CLAIM), Charité Universitätsmedizin Berlin, Berlin, Germany Lung Institute, Faculty of Medicine, Imperial College London, London, UK Centre for Medical Image Computing, Department of Computer Science, University College London, London, UK Department of Radiation Oncology, Duke University Medical Center, Durham, NC, USA Institute of Medical Technology, Peking University Health Science Center, Beijing, China Hangzhou Genlight MedTech Co., Ltd., China Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China Department of Automation, Shanghai Jiao Tong University, Shanghai, China Department of Artificial Intelligence, Sungkyunkwan University, Seoul, South Korea Department of Electrical Computer Engineering, Sungkyunkwan University, Seoul, South Korea Shanghai MediWorks Precision Instruments Co., Ltd., China Institute of Informatics, HES-SO Valais-Wallis, Switzerland Department of Measurement Electronics, AGH University of Krakow, Poland Laboratoire de Thermique et Energie de Nantes (LTeN), Université Nantes, Polytech’Nantes, Nantes, France Research Institute of Computer Vision Center for Precision Health, McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, USA Physense, BCN-Medtech, Department of Communication Information Technologies, Universitat Pompeu Fabra, Barcelona, Spain Department of Mathematical Modeling Machine Learning, University of Zurich, Zurich, Switzerland Laboratory of Brain Atlas Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences, Beijing, China School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China School of Computer Information Engineering, Xiamen University of Technology, Xiamen, China Vascular Research Center, University at Buffalo, NY, USA Department of Pathology Anatomical Sciences, University at Buffalo, NY, USA Department of Neurosurgery, University at Buffalo, NY, USA LPIXEL Inc., Tokyo, Japan

AI总结 组织TopCoW基准挑战,发布含125对MRA和CTA扫描的注释数据集,参与者提交CoW分割和变体分类算法,经评估,最佳算法在多任务中表现出色,证明CoW分割算法对下游临床应用有可解释性效用。

Comments Summary paper for the TopCoW Challenge: 4 figures, 1 table, and supplementary material in appendix. Accepted for publication in NEJM AI. Datasets and best-performing algorithm Dockers are available at https://zenodo.org/records/15692630 and https://zenodo.org/records/15665435

Journal ref NEJM AI 2026;3(8)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.17932 2026-07-14 cs.CL cs.AI 版本更新

Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA

在扩散大型语言模型中进行提示压缩:在LLDA上评估LLMLingua-2

Sterling Huang, Abigayle Brown, Jiyoo Noh, Jiakang Xu, Wantong Huo, Kaung Myat Kyaw, Jonathan Chan

机构 * University of Toronto(多伦多大学) King Mongkut’s University of Technology Thonburi(泰国科技理工学院)

AI总结 本文研究了提示压缩在扩散大型语言模型中的有效性,通过在LLDA上评估LLMLingua-2,发现提示压缩在数学推理任务中效果不佳,而摘要任务相对稳健,表明为扩散模型设计的提示压缩方法并不适用于所有场景。

Comments Accepted to appear in The 14th International Conference on Advances in Information Technology (IAIT2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.15133 2026-07-14 cs.LG 版本更新

Causal Foundation Models with Continuous Treatments

具有连续处理的因果基础模型

Christopher Stith, Medha Barath, Vahid Balazadeh, Jesse C. Cresswell, Rahul G. Krishnan

机构 * Layer 6 AI University of Toronto(多伦多大学) Vector Institute(向量研究所)

AI总结 本文提出首个连续处理因果基础模型,通过设计连续处理变量的数据生成先验,生成丰富因果训练语料,并利用Transformer重建个体治疗响应曲线,实现无需额外训练的因果效应预测。

Comments 21 pages, 9 figures; added link to inference code

详情

展开后加载摘要…

URL PDF HTML 收藏