arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

ETH Zurich(苏黎世联邦理工学院)

共收录 1407
2604.07666 2026-04-10 cs.LG cs.AI

An Imperfect Verifier is Good Enough: Learning with Noisy Rewards

完美验证者并非必需:在有噪声奖励下学习

Andreas Plesner, Francisco Guzmán, Anish Athalye

机构 * Handshake AI ETH Zurich(苏黎世联邦理工学院)

AI总结 研究通过引入噪声探讨强化学习在有噪声奖励下的鲁棒性,发现15%的噪声率下验证准确率接近干净基线,表明不完美验证不影响RLVR效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08016 2026-04-10 cs.CV cs.LG

Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs

视频并行扩展:聚合多样化的帧子集用于VideoLLMs

Hyungjin Chung, Hyelin Nam, Jiyeon Kim, Hyojun Go, Byeongjun Park, Junho Kim, Joonseok Lee, Seongsu Ha, Byung-Hoon Kim

机构 * EverEx University of Michigan(密歇根大学) KAIST(韩国科学技术院) ETH Zürich(苏黎世联邦理工学院) UNC Chapel Hill(北卡罗来纳大学教堂山分校) Yonsei University(延世大学)

AI总结 本文提出Video Parallel Scaling方法,通过并行处理不同帧子集提升VideoLLMs的时序推理能力,实验表明其在不同模型架构和规模上均显著提升性能,且比其他并行方法更高效。

Comments CVPR Findings 2026; code: https://github.com/hyungjin-chung/VPS

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07069 2026-04-09 eess.SY cs.LG cs.SY math.DS

Controller Design for Structured State-space Models via Contraction Theory

通过收缩理论设计结构状态空间模型的控制器

Muhammad Zakwan, Vaibhav Gupta, Alireza Karimi, Efe C. Balta, Giancarlo Ferrari-Trecate

机构 * Laboratoire d’Automatique, EPFL(EPFL自动控制实验室) Control & Automation Group, Inspire AG(Inspire AG控制与自动化组) Automatic Control Laboratory (IfA), ETH Zürich(苏黎世联邦理工学院自动控制实验室)

AI总结 本文提出了一种间接数据驱动的输出反馈控制器设计方法,利用结构状态空间模型作为替代模型,通过线性矩阵不等式和收缩理论实现可扩展的控制设计,并建立分离原理以独立设计观测器和状态反馈控制器。

Comments The first and second authors contributed equally. The paper has been accepted in 24th European Control Conference (ECC) in Reykjavik, Iceland, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.06972 2026-04-09 cs.RO cs.MA

Differentiable Environment-Trajectory Co-Optimization for Safe Multi-Agent Navigation

可微环境-轨迹联合优化用于安全多智能体导航

Zhan Gao, Gabriele Fadini, Stelian Coros, Amanda Prorok

机构 * University of Cambridge(剑桥大学) Zurich University of Applied Sciences, ZHAW(苏黎世应用科技大学) ETH Zurich(苏黎世联邦理工学院)

AI总结 本文提出一种可微环境-轨迹联合优化方法,通过双层优化问题提升多智能体导航的安全性和效率,实验验证了其在物流和交通场景中的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.06648 2026-04-09 astro-ph.GA cs.CV

Euclid Quick Data Release (Q1). AgileLens: A scalable CNN-based pipeline for strong gravitational lens identification

欧几里得快速数据发布(Q1)。AgileLens:一种可扩展的基于CNN的强引力透镜识别管道

Euclid Collaboration, X. Xu, R. Chen, T. Li, A. R. Cooray, S. Schuldt, J. A. Acevedo Barroso, D. Stern, D. Scott, M. Meneghetti, G. Despali, J. Chopra, Y. Cao, M. Cheng, J. Buda, J. Zhang, J. Furumizo, R. Valencia, Z. Jiang, C. Tortora, N. E. P. Lines, T. E. Collett, S. Fotopoulou, A. Galan, A. Manjón-García, R. Gavazzi, L. Iwamoto, S. Kruk, M. Millon, P. Nugent, C. Saulder, D. Sluse, J. Wilde, M. Walmsley, F. Courbin, R. B. Metcalf, B. Altieri, A. Amara, S. Andreon, N. Auricchio, C. Baccigalupi, M. Baldi, A. Balestra, S. Bardelli, P. Battaglia, R. Bender, A. Biviano, E. Branchini, M. Brescia, S. Camera, V. Capobianco, C. Carbone, V. F. Cardone, J. Carretero, S. Casas, M. Castellano, G. Castignani, S. Cavuoti, A. Cimatti, C. Colodro-Conde, G. Congedo, C. J. Conselice, L. Conversi, Y. Copin, H. M. Courtois, M. Cropper, A. Da Silva, H. Degaudenzi, G. De Lucia, C. Dolding, H. Dole, F. Dubath, X. Dupac, S. Dusini, S. Escoffier, M. Farina, R. Farinelli, S. Farrens, S. Ferriol, F. Finelli, P. Fosalba, M. Frailis, E. Franceschi, M. Fumana, S. Galeotta, K. George, W. Gillard, B. Gillis, C. Giocoli, P. Gómez-Alvarez, J. Gracia-Carpio, A. Grazian, F. Grupp, S. V. H. Haugan, W. Holmes, F. Hormuth, A. Hornstrup, K. Jahnke, M. Jhabvala, B. Joachimi, S. Kermiche, A. Kiessling, B. Kubik, M. Kümmel, M. Kunz, H. Kurki-Suonio, A. M. C. Le Brun, S. Ligori, P. B. Lilje, V. Lindholm, I. Lloro, G. Mainetti, E. Maiorano, O. Mansutti, S. Marcin, O. Marggraf, M. Martinelli, N. Martinet, F. Marulli, R. J. Massey, E. Medinaceli, S. Mei, M. Melchior, E. Merlin, G. Meylan, A. Mora, M. Moresco, L. Moscardini, R. Nakajima, C. Neissner, R. C. Nichol, S. -M. Niemi, J. W. Nightingale, C. Padilla, S. Paltani, F. Pasian, K. Pedersen, W. J. Percival, V. Pettorino, G. Polenta, M. Poncet, L. A. Popa, F. Raison, A. Renzi, J. Rhodes, G. Riccio, E. Romelli, M. Roncarelli, R. Saglia, Z. Sakr, D. Sapone, M. Schirmer, P. Schneider, T. Schrabback, A. Secroun, G. Seidel, E. Sihvola, P. Simon, C. Sirignano, G. Sirri, L. Stanco, P. Tallada-Crespí, A. N. Taylor, I. Tereno, N. Tessore, S. Toft, R. Toledo-Moreo, F. Torradeflot, I. Tutusaus, L. Valenziano, J. Valiviita, T. Vassallo, G. Verdoes Kleijn, A. Veropalumbo, Y. Wang, J. Weller, A. Zacchei, G. Zamorani, F. M. Zerbi, E. Zucca, M. Ballardini, M. Bolzonella, C. Burigana, R. Cabanac, M. Calabrese, A. Cappi, T. Castro, J. A. Escartin Vigo, L. Gabarra, S. Hemmati, J. Macias-Perez, R. Maoli, J. Martín-Fleitas, N. Mauri, P. Monaco, A. A. Nucita, A. Pezzotta, M. Pöntinen, I. Risso, V. Scottez, M. Sereno, M. Tenti, M. Tucci, M. Viel, M. Wiesmann, Y. Akrami, I. T. Andika, G. Angora, S. Anselmi, M. Archidiacono, F. Atrio-Barandela, L. Bazzanini, P. Bergamini, D. Bertacca, M. Bethermin, F. Beutler, L. Blot, S. Borgani, M. L. Brown, S. Bruton, A. Calabro, B. Camacho Quevedo, F. Caro, C. S. Carvalho, F. Cogato, S. Conseil, O. Cucciati, S. Davini, G. Desprez, A. Díaz-Sánchez, S. Di Domizio, J. M. Diego, P. -A. Duc, V. Duret, M. Y. Elkhashab, A. Enia, Y. Fang, A. Finoguenov, A. Franco, K. Ganga, T. Gasparetto, E. Gaztanaga, F. Giacomini, F. Gianotti, G. Gozaliasl, M. Guidi, C. M. Gutierrez, A. Hall, C. Hernández-Monteagudo, H. Hildebrandt, J. Hjorth, J. J. E. Kajava, Y. Kang, V. Kansal, D. Karagiannis, K. Kiiveri, J. Kim, C. C. Kirkpatrick, F. Lepori, G. Leroy, G. F. Lesci, J. Lesgourgues, T. I. Liaudat, S. J. Liu, M. Magliocchetti, E. A. Magnier, F. Mannucci, C. J. A. P. Martins, L. Maurin, M. Miluzio, C. Moretti, G. Morgante, K. Naidoo, A. Navarro-Alsina, S. Nesseris, D. Paoletti, F. Passalacqua, K. Paterson, L. Patrizii, A. Pisani, D. Potter, G. W. Pratt, S. Quai, M. Radovich, K. Rojas, W. Roster, S. Sacquegna, M. Sahlén, D. B. Sanders, E. Sarpa, C. Scarlata, A. Schneider, M. Schultheis, D. Sciotti, E. Sellentin, L. C. Smith, K. Tanidis, C. Tao, F. Tarsitano, G. Testera, R. Teyssier, S. Tosi, A. Troja, A. Venhola, D. Vergani, G. Vernardos, G. Verza, S. Vinciguerra, N. A. Walton, A. H. Wright, H. W. Yeung

机构 * Department of Physics \& Astronomy, University of California Irvine, Irvine CA 92697, USA aff1 University of Southern California, 3551 Trousdale Parkway, Los Angeles, CA 90089, USA aff2 Dipartimento di Fisica "Aldo Pontremoli", Universit\`a degli Studi di Milano, Via Celoria 16, 20133 Milano, Italy aff3 INAF-IASF Milano, Via Alfonso Corti 12, 20133 Milano, Italy aff4 Jet Propulsion Laboratory, California Institute of Technology, 4800 Oak Grove Drive, Pasadena, CA, 91109, USA aff5 Department of Physics Astronomy, University of British Columbia, Vancouver, BC V6T 1Z1, Canada aff6 INAF-Osservatorio di Astrofisica e Scienza dello Spazio di Bologna, Via Piero Gobetti 93/3, 40129 Bologna, Italy aff7 INFN-Sezione di Bologna, Viale Berti Pichat 6/2, 40127 Bologna, Italy aff8 Dipartimento di Fisica e Astronomia "Augusto Righi" - Alma Mater Studiorum Universit\`a di Bologna, via Piero Gobetti 93/2, 40129 Bologna, Italy aff9 INAF-Osservatorio Astronomico di Capodimonte, Via Moiariello 16, 80131 Napoli, Italy aff10 Institute of Cosmology Gravitation, University of Portsmouth, Portsmouth PO1 3FX, UK aff11 School of Physics, HH Wills Physics Laboratory, University of Bristol, Tyndall Avenue, Bristol, BS8 1TL, UK aff12 Max-Planck-Institut f\"ur Astrophysik, Karl-Schwarzschild-Str. 1, 85748 Garching, Germany aff13 Technical University of Munich, TUM School of Natural Sciences, Physics Department, James-Franck-Str. 1, 85748 Garching, Germany aff14 Departamento F\'isica Aplicada, Universidad Polit\'ecnica de Cartagena, Campus Muralla del Mar, 30202 Cartagena, Murcia, Spain aff15 Aix-Marseille Universit\'e, CNRS, CNES, LAM, Marseille, France aff16 Institut d'Astrophysique de Paris, UMR 7095, CNRS Sorbonne Universit\'e, 98 bis boulevard Arago, 75014 Paris, France aff17 Center for Astrophysics | Harvard \& Smithsonian, 60 Garden St., Cambridge, MA 02138, USA aff18 ESAC/ESA, Camino Bajo del Castillo, s/n., Urb. Villafranca del Castillo, 28692 Villanueva de la Ca\ nada, Madrid, Spain aff19 Universit\'e de Gen\`eve, D\'epartement de Physique Th\'eorique Centre for Astroparticle Physics, 24 quai Ernest-Ansermet, CH-1211 Gen\`eve 4, Switzerland aff20 Lawrence Berkeley National Laboratory, One Cyclotron Road, Berkeley, CA 94720, USA aff21 Max Planck Institute for Extraterrestrial Physics, Giessenbachstr. 1, 85748 Garching, Germany aff22 Universit\"ats-Sternwarte M\"unchen, Fakult\"at f\"ur Physik, Ludwig-Maximilians-Universit\"at M\"unchen, Scheinerstr. 1, 81679 M\"unchen, Germany aff23 STAR Institute, University of Li \`e ge, Quartier Agora, All\'ee du six Ao\ ut 19c, 4000 Li\`ege, Belgium aff24 Institut de Ci\` e ncies del Cosmos (ICCUB), Universitat de Barcelona (IEEC-UB), Mart\' i i Franqu\` e s 1, 08028 Barcelona, Spain aff25 David A. Dunlap Department of Astronomy \& Astrophysics, University of Toronto, 50 St George Street, Toronto, Ontario M5S 3H4, Canada aff26 Jodrell Bank Centre for Astrophysics, Department of Physics Astronomy, University of Manchester, Oxford Road, Manchester M13 9PL, UK aff27 Instituci\'o Catalana de Recerca i Estudis Avan c ats (ICREA), Passeig de Llu\' s Companys 23, 08010 Barcelona, Spain aff28 Institut de Ciencies de l'Espai (IEEC-CSIC), Campus UAB, Carrer de Can Magrans, s/n Cerdanyola del Vall\'es, 08193 Barcelona, Spain aff29 School of Mathematics Physics, University of Surrey, Guildford, Surrey, GU2 7XH, UK aff30 INAF-Osservatorio Astronomico di Brera, Via Brera 28, 20122 Milano, Italy aff31 IFPU, Institute for Fundamental Physics of the Universe, via Beirut 2, 34151 Trieste, Italy aff32 INAF-Osservatorio Astronomico di Trieste, Via G. B. Tiepolo 11, 34143 Trieste, Italy aff33 INFN, Sezione di Trieste, Via Valerio 2, 34127 Trieste TS, Italy aff34 SISSA, International School for Advanced Studies, Via Bonomea 265, 34136 Trieste TS, Italy aff35 Dipartimento di Fisica e Astronomia, Universit\`a di Bologna, Via Gobetti 93/2, 40129 Bologna, Italy aff36 INAF-Osservatorio Astronomico di Padova, Via dell'Osservatorio 5, 35122 Padova, Italy aff37 Dipartimento di Fisica, Universit\`a di Genova, Via Dodecaneso 33, 16146, Genova, Italy aff38 INFN-Sezione di Genova, Via Dodecaneso 33, 16146, Genova, Italy aff39 Department of Physics "E. Pancini", University Federico II, Via Cinthia 6, 80126, Napoli, Italy aff40 Dipartimento di Fisica, Universit\`a degli Studi di Torino, Via P. Giuria 1, 10125 Torino, Italy aff41 INFN-Sezione di Torino, Via P. Giuria 1, 10125 Torino, Italy aff42 INAF-Osservatorio Astrofisico di Torino, Via Osservatorio 20, 10025 Pino Torinese (TO), Italy aff43 INAF-Osservatorio Astronomico di Roma, Via Frascati 33, 00078 Monteporzio Catone, Italy aff44 INFN-Sezione di Roma, Piazzale Aldo Moro, 2 - c/o Dipartimento di Fisica, Edificio G. Marconi, 00185 Roma, Italy aff45 Centro de Investigaciones Energ\'eticas, Medioambientales y Tecnol\'ogicas (CIEMAT), Avenida Complutense 40, 28040 Madrid, Spain aff46 Port d'Informaci\' o Cient\' i fica, Campus UAB, C. Albareda s/n, 08193 Bellaterra (Barcelona), Spain aff47 Institute for Theoretical Particle Physics Cosmology (TTK), RWTH Aachen University, 52056 Aachen, Germany aff48 Deutsches Zentrum f\"ur Luft- und Raumfahrt e. V. (DLR), Linder H\"ohe, 51147 K\"oln, Germany aff49 INFN section of Naples, Via Cinthia 6, 80126, Napoli, Italy aff50 Dipartimento di Fisica e Astronomia "Augusto Righi" - Alma Mater Studiorum Universit\`a di Bologna, Viale Berti Pichat 6/2, 40127 Bologna, Italy aff51 Instituto de Astrof\' sica de Canarias, E-38205 La Laguna, Tenerife, Spain aff52 Institute for Astronomy, University of Edinburgh, Royal Observatory, Blackford Hill, Edinburgh EH9 3HJ, UK aff53 European Space Agency/ESRIN, Largo Galileo Galilei 1, 00044 Frascati, Roma, Italy aff54 Universit\'e Claude Bernard Lyon 1, CNRS/IN2P3, IP2I Lyon, UMR 5822, Villeurbanne, F-69100, France aff55 UCB Lyon 1, CNRS/IN2P3, IUF, IP2I Lyon, 4 rue Enrico Fermi, 69622 Villeurbanne, France aff56 Mullard Space Science Laboratory, University College London, Holmbury St Mary, Dorking, Surrey RH5 6NT, UK aff57 Departamento de F\'isica, Faculdade de Ci\ encias, Universidade de Lisboa, Edif\'icio C8, Campo Grande, PT1749-016 Lisboa, Portugal aff58 Instituto de Astrof\'isica e Ci\ encias do Espa c o, Faculdade de Ci\ encias, Universidade de Lisboa, Campo Grande, 1749-016 Lisboa, Portugal aff59 Department of Astronomy, University of Geneva, ch. d'Ecogia 16, 1290 Versoix, Switzerland aff60 Universit\'e Paris-Saclay, CNRS, Institut d'astrophysique spatiale, 91405, Orsay, France aff61 INFN-Padova, Via Marzolo 8, 35131 Padova, Italy aff62 Aix-Marseille Universit\'e, CNRS/IN2P3, CPPM, Marseille, France aff63 INAF-Istituto di Astrofisica e Planetologia Spaziali, via del Fosso del Cavaliere, 100, 00100 Roma, Italy aff64 Universit\'e Paris-Saclay, Universit\'e Paris Cit\'e, CEA, CNRS, AIM, 91191, Gif-sur-Yvette, France aff65 INFN-Bologna, Via Irnerio 46, 40126 Bologna, Italy aff66 Institut d'Estudis Espacials de Catalunya (IEEC), Edifici RDIT, Campus UPC, 08860 Castelldefels, Barcelona, Spain aff67 Institute of Space Sciences (ICE, CSIC), Campus UAB, Carrer de Can Magrans, s/n, 08193 Barcelona, Spain aff68 University Observatory, LMU Faculty of Physics, Scheinerstr. 1, 81679 Munich, Germany aff69 FRACTAL S.L.N.E., calle Tulip\'an 2, Portal 13 1A, 28231, Las Rozas de Madrid, Spain aff70 Institute of Theoretical Astrophysics, University of Oslo, P.O. Box 1029 Blindern, 0315 Oslo, Norway aff71 Felix Hormuth Engineering, Goethestr. 17, 69181 Leimen, Germany aff72 Technical University of Denmark, Elektrovej 327, 2800 Kgs. Lyngby, Denmark aff73 Cosmic Dawn Center (DAWN), Denmark aff74 Max-Planck-Institut f\"ur Astronomie, K\"onigstuhl 17, 69117 Heidelberg, Germany aff75 NASA Goddard Space Flight Center, Greenbelt, MD 20771, USA aff76 Department of Physics Astronomy, University College London, Gower Street, London WC1E 6BT, UK aff77 Department of Physics, P.O. Box 64, University of Helsinki, 00014 Helsinki, Finland aff78 Helsinki Institute of Physics, Gustaf H \"a llstr \"o min katu 2, University of Helsinki, 00014 Helsinki, Finland aff79 Laboratoire d'etude de l'Univers et des phenomenes eXtremes, Observatoire de Paris, Universit\'e PSL, Sorbonne Universit\'e, CNRS, 92190 Meudon, France aff80 SKAO, Jodrell Bank, Lower Withington, Macclesfield SK11 9FT, UK aff81 Centre de Calcul de l'IN2P3/CNRS, 21 avenue Pierre de Coubertin 69627 Villeurbanne Cedex, France aff82 University of Applied Sciences Arts of Northwestern Switzerland, School of Computer Science, 5210 Windisch, Switzerland aff83 Universit\"at Bonn, Argelander-Institut f\"ur Astronomie, Auf dem H\"ugel 71, 53121 Bonn, Germany aff84 Department of Physics, Institute for Computational Cosmology, Durham University, South Road, Durham, DH1 3LE, UK aff85 Universit\'e Paris Cit\'e, CNRS, Astroparticule et Cosmologie, 75013 Paris, France aff86 CNRS-UCB International Research Laboratory, Centre Pierre Bin\'etruy, IRL2007, CPB-IN2P3, Berkeley, USA aff87 University of Applied Sciences Arts of Northwestern Switzerland, School of Engineering, 5210 Windisch, Switzerland aff88 Institute of Physics, Laboratory of Astrophysics, Ecole Polytechnique F\'ed\'erale de Lausanne (EPFL), Observatoire de Sauverny, 1290 Versoix, Switzerland aff89 Telespazio UK S.L. for European Space Agency (ESA), Camino bajo del Castillo, s/n, Urbanizacion Villafranca del Castillo, Villanueva de la Ca\ nada, 28692 Madrid, Spain aff90 Institut de F\' i sica d'Altes Energies (IFAE), The Barcelona Institute of Science Technology, Campus UAB, 08193 Bellaterra (Barcelona), Spain aff91 European Space Agency/ESTEC, Keplerlaan 1, 2201 AZ Noordwijk, The Netherlands aff92 School of Mathematics, Statistics Physics, Newcastle University, Herschel Building, Newcastle-upon-Tyne, NE1 7RU, UK aff93 DARK, Niels Bohr Institute, University of Copenhagen, Jagtvej 155, 2200 Copenhagen, Denmark aff94 Waterloo Centre for Astrophysics, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada aff95 Department of Physics Astronomy, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada aff96 Perimeter Institute for Theoretical Physics, Waterloo, Ontario N2L 2Y5, Canada aff97 Space Science Data Center, Italian Space Agency, via del Politecnico snc, 00133 Roma, Italy aff98 Centre National d'Etudes Spatiales -- Centre spatial de Toulouse, 18 avenue Edouard Belin, 31401 Toulouse Cedex 9, France aff99 Institute of Space Science, Str. Atomistilor, nr. 409 M a gurele, Ilfov, 077125, Romania aff100 Dipartimento di Fisica e Astronomia "G. Galilei", Universit\`a di Padova, Via Marzolo 8, 35131 Padova, Italy aff101 Instituto de F\'isica Te\'orica UAM-CSIC, Campus de Cantoblanco, 28049 Madrid, Spain aff102 Institut de Recherche en Astrophysique et Plan\'etologie (IRAP), Universit\'e de Toulouse, CNRS, UPS, CNES, 14 Av. Edouard Belin, 31400 Toulouse, France aff103 Universit\'e St Joseph Faculty of Sciences, Beirut, Lebanon aff104 Departamento de F\'isica, FCFM, Universidad de Chile, Blanco Encalada 2008, Santiago, Chile aff105 Universit\"at Innsbruck, Institut f\"ur Astro- und Teilchenphysik, Technikerstr. 25/8, 6020 Innsbruck, Austria aff106 Department of Physics Helsinki Institute of Physics, Gustaf H\"allstr\"omin katu 2, University of Helsinki, 00014 Helsinki, Finland aff107 Instituto de Astrof\'isica e Ci\ encias do Espa c o, Faculdade de Ci\ encias, Universidade de Lisboa, Tapada da Ajuda, 1349-018 Lisboa, Portugal aff108 Cosmic Dawn Center (DAWN) aff109 Niels Bohr Institute, University of Copenhagen, Jagtvej 128, 2200 Copenhagen, Denmark aff110 Universidad Polit\'ecnica de Cartagena, Departamento de Electr\'onica y Tecnolog\'ia de Computadoras, Plaza del Hospital 1, 30202 Cartagena, Spain aff111 Kapteyn Astronomical Institute, University of Groningen, PO Box 800, 9700 AV Groningen, The Netherlands aff112 Caltech/IPAC, 1200 E. California Blvd., Pasadena, CA 91125, USA aff113 Dipartimento di Fisica e Scienze della Terra, Universit\`a degli Studi di Ferrara, Via Giuseppe Saragat 1, 44122 Ferrara, Italy aff114 Istituto Nazionale di Fisica Nucleare, Sezione di Ferrara, Via Giuseppe Saragat 1, 44122 Ferrara, Italy aff115 INAF, Istituto di Radioastronomia, Via Piero Gobetti 101, 40129 Bologna, Italy aff116 Astronomical Observatory of the Autonomous Region of the Aosta Valley (OAVdA), Loc. Lignan 39, I-11020, Nus (Aosta Valley), Italy aff117 Universit\'e C\ o te d'Azur, Observatoire de la C\ o te d'Azur, CNRS, Laboratoire Lagrange, Bd de l'Observatoire, CS 34229, 06304 Nice cedex 4, France aff118 ICSC - Centro Nazionale di Ricerca in High Performance Computing, Big Data e Quantum Computing, Via Magnanelli 2, Bologna, Italy aff119 Department of Physics, Oxford University, Keble Road, Oxford OX1 3RH, UK aff120 Univ. Grenoble Alpes, CNRS, Grenoble INP, LPSC-IN2P3, 53, Avenue des Martyrs, 38000, Grenoble, France aff121 Dipartimento di Fisica, Sapienza Universit\`a di Roma, Piazzale Aldo Moro 2, 00185 Roma, Italy aff122 Aurora Technology for European Space Agency (ESA), Camino bajo del Castillo, s/n, Urbanizacion Villafranca del Castillo, Villanueva de la Ca\ nada, 28692 Madrid, Spain aff123 Dipartimento di Fisica - Sezione di Astronomia, Universit\`a di Trieste, Via Tiepolo 11, 34131 Trieste, Italy aff124 Department of Mathematics Physics E. De Giorgi, University of Salento, Via per Arnesano, CP-I93, 73100, Lecce, Italy aff125 INFN, Sezione di Lecce, Via per Arnesano, CP-193, 73100, Lecce, Italy aff126 INAF-Sezione di Lecce, c/o Dipartimento Matematica e Fisica, Via per Arnesano, 73100, Lecce, Italy aff127 Institut d'Astrophysique de Paris, 98bis Boulevard Arago, 75014, Paris, France aff128 ICL, Junia, Universit\'e Catholique de Lille, LITL, 59000 Lille, France aff129 CERCA/ISO, Department of Physics, Case Western Reserve University, 10900 Euclid Avenue, Cleveland, OH 44106, USA aff130 Laboratoire Univers et Th\'eorie, Observatoire de Paris, Universit\'e PSL, Universit\'e Paris Cit\'e, CNRS, 92190 Meudon, France aff131 INFN-Sezione di Milano, Via Celoria 16, 20133 Milano, Italy aff132 Departamento de F \' sica Fundamental. Universidad de Salamanca. Plaza de la Merced s/n. 37008 Salamanca, Spain aff133 Universit\'e de Strasbourg, CNRS, Observatoire astronomique de Strasbourg, UMR 7550, 67000 Strasbourg, France aff134 Center for Data-Driven Discovery, Kavli IPMU (WPI), UTIAS, The University of Tokyo, Kashiwa, Chiba 277-8583, Japan aff135 California Institute of Technology, 1200 E California Blvd, Pasadena, CA 91125, USA aff136 Instituto de F\'isica de Cantabria, Edificio Juan Jord\'a, Avenida de los Castros, 39005 Santander, Spain aff137 Department of Computer Science, Aalto University, PO Box 15400, Espoo, FI-00 076, Finland aff138 Universidad de La Laguna, Dpto. Astrof\' sica, E-38206 La Laguna, Tenerife, Spain aff139 Ruhr University Bochum, Faculty of Physics Astronomy, Astronomical Institute (AIRUB), German Centre for Cosmological Lensing (GCCL), 44780 Bochum, Germany aff140 Department of Physics Astronomy, Vesilinnantie 5, University of Turku, 20014 Turku, Finland aff141 Finnish Centre for Astronomy with ESO (FINCA), Quantum, Vesilinnantie 5, University of Turku, 20014 Turku, Finland aff142 Serco for European Space Agency (ESA), Camino bajo del Castillo, s/n, Urbanizacion Villafranca del Castillo, Villanueva de la Ca\ nada, 28692 Madrid, Spain aff143 ARC Centre of Excellence for Dark Matter Particle Physics, Melbourne, Australia aff144 Centre for Astrophysics \& Supercomputing, Swinburne University of Technology, Hawthorn, Victoria 3122, Australia aff145 Department of Physics Astronomy, University of the Western Cape, Bellville, Cape Town, 7535, South Africa aff146 Departement of Theoretical Physics, University of Geneva, Switzerland aff147 Department of Physics, Centre for Extragalactic Astronomy, Durham University, South Road, Durham, DH1 3LE, UK aff148 IRFU, CEA, Universit\'e Paris-Saclay 91191 Gif-sur-Yvette Cedex, France aff149 Institute for Astronomy, University of Hawaii, 2680 Woodlawn Drive, Honolulu, HI 96822, USA aff150 INAF-Osservatorio Astrofisico di Arcetri, Largo E. Fermi 5, 50125, Firenze, Italy aff151 Centro de Astrof\' sica da Universidade do Porto, Rua das Estrelas, 4150-762 Porto, Portugal aff152 Instituto de Astrof\'isica e Ci\ encias do Espa c o, Universidade do Porto, CAUP, Rua das Estrelas, PT4150-762 Porto, Portugal aff153 HE Space for European Space Agency (ESA), Camino bajo del Castillo, s/n, Urbanizacion Villafranca del Castillo, Villanueva de la Ca\ nada, 28692 Madrid, Spain aff154 Department of Astrophysics, University of Zurich, Winterthurerstrasse 190, 8057 Zurich, Switzerland aff155 INAF - Osservatorio Astronomico d'Abruzzo, Via Maggini, 64100, Teramo, Italy aff156 Theoretical astrophysics, Department of Physics Astronomy, Uppsala University, Box 516, 751 37 Uppsala, Sweden aff157 Minnesota Institute for Astrophysics, University of Minnesota, 116 Church St SE, Minneapolis, MN 55455, USA aff158 Mathematical Institute, University of Leiden, Einsteinweg 55, 2333 CA Leiden, The Netherlands aff159 Leiden Observatory, Leiden University, Einsteinweg 55, 2333 CC Leiden, The Netherlands aff160 Institute of Astronomy, University of Cambridge, Madingley Road, Cambridge CB3 0HA, UK aff161 Center for Astrophysics Cosmology, University of Nova Gorica, Nova Gorica, Slovenia aff162 Institute for Particle Physics Astrophysics, Dept. of Physics, ETH Zurich, Wolfgang-Pauli-Strasse 27, 8093 Zurich, Switzerland aff163 Department of Astrophysical Sciences, Peyton Hall, Princeton University, Princeton, NJ 08544, USA aff164 Space physics astronomy research unit, University of Oulu, Pentti Kaiteran katu 1, FI-90014 Oulu, Finland aff165 Department of Physics Astronomy, Lehman College of the CUNY, Bronx, NY 10468, USA aff166 American Museum of Natural History, Department of Astrophysics, New York, NY 10024, USA aff167 International Centre for Theoretical Physics (ICTP), Strada Costiera 11, 34151 Trieste, Italy aff168 Center for Computational Astrophysics, Flatiron Institute, 162 5th Avenue, 10010, New York, NY, USA aff169

AI总结 本文提出了一种基于CNN的高效强引力透镜识别方法,通过迭代优化和数据增强,从欧几里得Q1数据中识别出441个候选系统,其中311个与现有目录重合,130个为新增,方法可扩展至未来数据发布。

Comments 30 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.06467 2026-04-09 cs.CV

PhysHead: Simulation-Ready Gaussian Head Avatars

PhysHead: 可模拟的高斯头部化身

Berna Kabadayi, Vanessa Sklyarova, Wojciech Zielonka, Justus Thies, Gerard Pons-Moll

机构 * Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所) ETH Zürich(苏黎世联邦理工学院) University of Tübingen(图宾根大学) Technical University of Darmstadt(达姆施塔特工业大学) Tübingen AI Center(图宾根人工智能中心) Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

AI总结 本文提出PhysHead,一种结合3D参数网格和发丝的混合表示方法,用于生成具有真实发丝动态的可动画头部化身,通过多视角视频学习实现逼真发丝运动。

Comments Project Page: see https://phys-head.github.io/; Youtube Video: see https://www.youtube.com/watch?v=k68fsSSwzc0; Accepted to CVPR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10303 2026-04-09 stat.ML cs.LG stat.CO stat.ME

MF-GLaM: A multifidelity stochastic emulator using generalized lambda models

MF-GLaM:一种基于广义lambda模型的多保真度随机模拟器

K. Giannoukou, X. Zhu, S. Marelli, B. Sudret

机构 * Chair of Risk, Safety and Uncertainty Quantification, ETH Zürich(苏黎世联邦理工学院风险、安全与不确定性量化教席) Laboratory of Signals and Systems, CentraleSupélec, Université Paris-Saclay(巴黎萨克雷大学中央理工-高等电力学院信号与系统实验室)

AI总结 本文提出MF-GLaM,利用低保真度模拟器数据高效建模高保真度随机模拟器的条件响应分布,实现更准确的预测。

Journal ref Computer Methods in Applied Mechanics and Engineering, Volume 448, Part B, January 2026, 118498

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.02249 2026-04-09 cs.LG

Don't Label Twice: Quantity Beats Quality when Comparing Binary Classifiers on a Budget

不要两次标注:在预算下比较二分类器时数量胜过质量

Florian E. Dorner, Moritz Hardt

机构 * Max Planck Institute for Intelligent Systems, Tübingen(马克斯·普朗克智能系统研究所,蒂宾根) Tübingen AI Center(蒂宾根人工智能中心) ETH Zürich(苏黎世联邦理工学院)

AI总结 研究如何在预算内有效利用噪声标签比较两个二分类器的准确性,证明在选择更优分类器时,应优先收集更多样本的单一标签而非多个标签的多数投票。

Comments 34 pages, 3 Figures, Published at ICML 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.19469 2026-04-08 cs.CE cs.LG

GLUE: Coordinating Pre-Trained Generative Models for System-Level Design

GLUE:协调预训练生成模型进行系统级设计

Tim Aebersold, Soheyl Massoudi, Mark D. Fuge

机构 * Department of Engineering, University of [REDACTED]([已编辑]大学工程系) Department of Mechanical and Process Engineering, ETH Zurich(苏黎世联邦理工学院机械与过程工程系)

AI总结 本文提出GLUE方法,通过协调预训练生成模型生成可行、多样且高性能的系统设计,对比了数据驱动和无数据方法的性能与效率。

Comments 12 pages, 10 figures, Preprint

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.05230 2026-04-08 cs.LG cs.AI cs.NA math.NA math.OC

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks

曲率感知优化用于高精度物理信息神经网络

Anas Jnini, Elham Kiyani, Khemraj Shukla, Jorge F. Urban, Nazanin Ahmadi Daryakenari, Johannes Muller, Marius Zeinhofer, George Em Karniadakis

机构 * Department of Information Engineering and Computer Science, University of Trento(特伦托大学信息工程与计算机科学系) Division of Applied Mathematics, Brown University(布朗大学应用数学部) Center for Biomedical Engineering, Brown University(布朗大学生物医学工程中心) Institute of Mathematics, TU Berlin(柏林工业大学数学研究所) ETH Zurich(苏黎世联邦理工学院)

AI总结 本文提出曲率感知优化策略,加速物理信息神经网络求解偏微分方程和常微分方程,采用自然梯度、自缩放BFGS和Broyden优化器,并与高阶数值方法对比验证。

Comments 54 pages, 24 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.03181 2026-04-08 cs.RO eess.SP

Robotic Grasping and Placement Controlled by EEG-Based Hybrid Visual and Motor Imagery

基于EEG的混合视觉和运动想象的机器人抓取与放置控制

Yichang Liu, Tianyu Wang, Ziyi Ye, Yawei Li, Yu-Gang Jiang, Shouyan Wang, Yanwei Fu

机构 * Institute of Science and Technology for Brain-inspired Intelligence (ISTBI), Fudan University(复旦大学类脑智能科学与技术研究院) School of Data Science, Fudan University(复旦大学大数据学院) Institute of Trustworthy Embodied AI, Fudan University(复旦大学可信具身智能研究院) Shanghai Key Laboratory of Multimodal Embodied AI(上海市多模态具身智能重点实验室) Shanghai Innovation Institute(上海创新研究院) ETH Zürich(苏黎世联邦理工学院)

AI总结 本文提出一种整合EEG视觉和运动想象与机器人控制的框架,实现实时意图驱动的抓取与放置。系统通过离线预训练解码器在在线流式管道中零样本方式实现神经信号与物理控制的连接,实现视觉意图到机器人动作的转换,验证了纯想象基BCI范式在实际人机协作中的灵活性。

Comments ICRA 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.06928 2026-04-08 cs.CV

RenderFlow: Single-Step Neural Rendering via Flow Matching

RenderFlow:通过流匹配实现单步神经渲染

Shenghao Zhang, Runtao Liu, Christopher Schroers, Yang Zhang

机构 * Disney Research|Studios(迪士尼研究院/工作室) ETH Zürich(苏黎世联邦理工学院)

AI总结 本文提出RenderFlow框架,通过流匹配方法实现单步神经渲染,解决传统渲染方法的效率与精度问题,提升渲染质量和视觉效果。

Comments CVPR 2026; Supplementary material included

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.04898 2026-04-07 cs.AI cs.CL cs.LG

QED-Nano: Teaching a Tiny Model to Prove Hard Theorems

QED-Nano:用小型模型证明难题定理

LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching, Jia Li, Ian Wu, Lewis Tunstall, Aviral Kumar

机构 * CMU(卡内基梅隆大学) Hugging Face ETH Zurich(苏黎世联邦理工学院) Project Numina

AI总结 本文提出QED-Nano模型,通过三个阶段训练在数学竞赛证明任务中超越大模型,以较低成本实现高性能证明生成。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.07985 2026-04-07 cs.LG cs.AI cs.CR

Fewer Weights, More Problems: A Practical Attack on LLM Pruning

更少的权重,更多的问题:对LLM剪枝的一种实用攻击

Kazuki Egashira, Robin Staab, Thibaud Gloaguen, Mark Vero, Martin Vechev

机构 * ETH Zurich(苏黎世联邦理工学院)

AI总结 本文首次揭示了现代LLM剪枝方法可能被恶意利用的问题,通过构造看似无害的模型,在剪枝后表现出恶意行为,展示了剪枝过程中的安全风险。

Comments ICLR 2026. Code: https://github.com/eth-sri/llm-pruning-attack

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03696 2026-04-07 cs.CV

FunFact: Building Probabilistic Functional 3D Scene Graphs via Factor-Graph Reasoning

FunFact:通过因子图推理构建概率性功能3D场景图

Zhengyu Fu, René Zurbrügg, Kaixian Qu, Marc Pollefeys, Marco Hutter, Hermann Blum, Zuria Bauer

机构 * ETH Zürich(苏黎世联邦理工学院) Microsoft(微软) University of Bonn & Lamarr Institute(波恩大学与拉马尔研究所)

AI总结 FunFact通过因子图推理构建概率性功能3D场景图,结合语义和几何先验,提升场景功能理解的鲁棒性与准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03587 2026-04-07 cs.CR cs.AI

SecPI: Secure Code Generation with Reasoning Models via Security Reasoning Internalization

SecPI: 通过安全推理内化实现安全代码生成

Hao Wang, Niels Mündler, Mark Vero, Jingxuan He, Dawn Song, Martin Vechev

机构 * University of California, Berkeley(加州大学伯克利分校) ETH Zurich(苏黎世联邦理工学院)

AI总结 SecPI通过内化结构化安全推理,使推理模型在无需安全指令的情况下生成安全代码,经验证在多个安全基准测试中显著提升代码功能正确性和安全性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.03388 2026-04-07 cs.LG stat.ML

Scalable Variational Bayesian Fine-Tuning of LLMs via Orthogonalized Low-Rank Adapters

通过正交化低秩适配器实现大规模语言模型的可扩展变分贝叶斯微调

Haotian Xiang, Bingcong Li, Qin Lu

机构 * School of Electrical and Computer Engineering, University of Georgia(佐治亚大学电气与计算机工程学院) Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系)

AI总结 本文提出PoLAR-VBLL框架,通过正交化低秩适配器与变分推断结合,实现大规模语言模型的可扩展贝叶斯微调,提升不确定性量化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.11919 2026-04-07 stat.ME cs.AI math.ST stat.TH

A fine-grained look at causal effects in causal spaces

对因果空间中因果效应的细致探讨

Junhyung Park, Yuqing Zhou

机构 * ETH Zürich, Switzerland(瑞士苏黎世联邦理工学院)

AI总结 本文从事件层面探讨因果效应,引入事件和sigma-algebra的定义,证明因果效应与干预措施下的独立性关系,并提出量化措施以评估因果效应的强度与性质。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.23230 2026-04-07 cs.CV

Action-guided generation of 3D functionality segmentation data

基于动作的3D功能分割数据生成

Jaime Corsetti, Francesco Giuliari, Davide Boscaini, Pedro Hermosilla, Andrea Pilzer, Guofeng Mei, Alexandros Delitzas, Francis Engelmann, Fabio Poiesi

机构 * Fondazione Bruno Kessler(布鲁诺·凯斯勒基金会) University of Trento(特伦托大学) TU Wien(维也纳工业大学) NVIDIA(英伟达) ETH Zurich(苏黎世联邦理工学院) MPI for Informatics(马克斯·普朗克信息学研究所) Stanford University(斯坦福大学) USI Lugano(卢加诺大学)

AI总结 本文提出SynthFun3D,通过动作描述生成3D功能分割数据,解决真实数据稀缺问题,提升3D功能理解性能。

Comments Accepted at CVPR 2026 GenRecon3D workshop. 17 pages, 8 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09104 2026-04-07 cs.RO

Decoupling Torque and Stiffness: A Unified Modeling and Control Framework for Antagonistic Artificial Muscles

解除扭矩与刚度的耦合:一种用于对抗性人工肌肉的统一建模与控制框架

Amirhossein Kazemipour, Robert K. Katzschmann

机构 * Soft Robotics Lab, IRIS, D-MAVT, ETH Zurich, Switzerland(瑞士苏黎世联邦理工学院D-MAVT系IRIS软体机器人实验室)

AI总结 本文提出了一种统一的实时框架,用于处理不同类型的人工肌肉,通过分离的Padé力模型、级联逆动力学控制器和生物启发的深度自适应交互策略,实现独立的扭矩和刚度控制。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.02260 2026-04-03 cs.LG cs.RO

Model-Based Reinforcement Learning for Control under Time-Varying Dynamics

基于模型的强化学习用于时间变化动态下的控制

Klemens Iten, Bruce Lee, Chenhao Li, Lenart Treven, Andreas Krause, Bhavya Sukhija

机构 * ETH Zürich(苏黎世联邦理工学院) ETH AI Center(苏黎世联邦理工学院人工智能中心)

AI总结 本文研究了在时间变化动态下基于模型的强化学习控制,通过高斯过程动态模型分析,提出适应性数据缓冲机制的算法,提升了非平稳动态连续控制任务的性能。

Comments 15 pages, 5 figues, 2 tables. This work has been submitted to the IEEE for possible publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.29399 2026-04-03 cs.AI cs.DB

ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities

ELT-Bench-Verified: 评估质量问题低估了AI代理的能力

Christopher Zanoli, Andrea Giovannini, Tengjun Jin, Ana Klimovic, Yotam Perlitz

机构 * IBM Research(IBM研究院) ETH Zurich(苏黎世联邦理工学院) University of Illinois (UIUC)(伊利诺伊大学厄巴纳-香槟分校)

AI总结 本文通过重新评估ELT-Bench发现代理能力被低估,提出Auditor-Corrector方法修正评估质量,构建ELT-Bench-Verified提升评估准确性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.02074 2026-04-03 stat.AP cs.CV

Country-wide, high-resolution monitoring of forest browning with Sentinel-2

全国范围内的高分辨率森林枯黄监测:利用哨兵-2卫星

Samantha Biegel, David Brüggemann, Francesco Grossi, Michele Volpi, Konrad Schindler, Benjamin D. Stocker

机构 * ETH Zurich(苏黎世联邦理工学院) ETH AI Center(ETH人工智能中心) Swiss Data Science Center(瑞士数据科学中心) EPFL(洛桑联邦理工学院) Swiss Federal Institute for Forest, Snow and Landscape Research WSL(瑞士联邦森林、雪与景观研究所) University of Bern(伯尔尼大学) Oeschger Centre for Climate Change Research(厄施格气候变化研究中心)

AI总结 本文提出一种可扩展方法,利用哨兵-2卫星数据在10米分辨率下对森林绿度异常进行全国范围监测,通过植被周期模型检测瑞士森林枯黄现象,模型解释了65%的观测变化。

Comments 9 pages, 7 figures, to be published in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS Congress)

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01421 2026-04-03 cs.CV

EgoFlow: Gradient-Guided Flow Matching for Egocentric 6DoF Object Motion Generation

EgoFlow:基于梯度的流匹配用于第一人称6自由度物体运动生成

Abhishek Saroha, Huajian Zeng, Xingxing Zuo, Daniel Cremers, Xi Wang

机构 * TU München(慕尼黑工业大学) MCML(慕尼黑机器学习中心) ETH Zürich(苏黎世联邦理工学院) MBZUAI(穆罕默德·本·扎耶德人工智能大学)

AI总结 本文提出EgoFlow,通过多模态第一人称观察生成物理合理的物体运动轨迹,结合Mamba-Transformer-Perceiver架构和梯度引导推理,提升运动生成的准确性和物理真实性。

Comments CVPR 2026: https://abhi-rf.github.io/egoflow/

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.15033 2026-04-03 cs.LG

Rethinking Machine Unlearning: Models Designed to Forget via Key Deletion

重新思考机器遗忘:为遗忘而设计的模型

Sonia Laguna, Jorge da Silva Goncalves, Moritz Vandenhirtz, Alain Ryser, Irene Cannistraci, Julia E. Vogt

机构 * Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系)

AI总结 本文提出了一种新的机器遗忘方法,通过设计使模型具备遗忘能力。MUNKEY模型通过删除实例标识符实现直接零样本遗忘,无需权重更新或原始数据访问,在多个数据集上优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.22294 2026-04-03 cs.CV cs.LG

Structure is Supervision: Multiview Masked Autoencoders for Radiology

结构是监督:用于放射学的多视图掩码自编码器

Sonia Laguna, Andrea Agostini, Alain Ryser, Samuel Ruiperez-Campillo, Irene Cannistraci, Moritz Vandenhirtz, Stephan Mandt, Nicolas Deperrois, Farhad Nooralahzadeh, Michael Krauthammer, Thomas M. Sutter, Julia E. Vogt

机构 * Department of Computer Science, ETH Zurich(苏黎世联邦理工学院计算机科学系) Department of Computer Science, UC Irvine(加州大学尔湾分校计算机科学系) Department of Quantitative Biomedicine, University of Zurich(苏黎世大学定量生物医学系)

AI总结 本文提出多视图掩码自编码器(MVMAE),通过利用放射学研究的多视图结构学习视图不变和疾病相关表征,并在三个公开数据集上验证了其在疾病分类任务中的优越性能。

Journal ref Transactions on Machine Learning Research (TMLR) 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.20755 2026-04-03 cs.LG cs.AI stat.ML

Provable Benefits of In-Tool Learning for Large Language Models

大语言模型中工具学习的可证明优势

Sam Houliston, Ambroise Odonnat, Charles Arnal, Vivien Cabannes

机构 * ETH Zürich(苏黎世联邦理工学院) Inria, Univ. Rennes 2(法国国家信息与自动化研究所,雷恩第二大学) FAIR at Meta(Meta FAIR实验室)

AI总结 本文探讨了工具学习在事实回忆中的优势,证明通过工具可实现无限制的事实回忆,优于单纯记忆。

Journal ref ICLR 2026 MemAgents Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12864 2026-04-03 cs.CL cs.AI cs.LG

LEXam: Benchmarking Legal Reasoning on 340 Law Exams

LEXam:基于340法律考试的法律推理基准测试

Yu Fan, Jingwei Ni, Jakob Merane, Yang Tian, Yoan Hermstrüwer, Yinya Huang, Mubashara Akhtar, Etienne Salimbeni, Florian Geering, Oliver Dreyer, Daniel Brunner, Markus Leippold, Mrinmaya Sachan, Alexander Stremitzer, Christoph Engel, Elliott Ash, Joel Niklaus

机构 * ETH Zurich(苏黎世联邦理工学院) University of Zurich(苏黎世大学) University of Lausanne(洛桑大学) Max Planck Institute for Research on Collective Goods(马克斯·普朗克集体物品研究所) Omnilex University of St. Gallen(圣加仑大学) Swiss Federal Supreme Court(瑞士联邦最高法院)

AI总结 LEXam基准测试通过340法律考试数据,包含7537道英语和德语法律考试题目,涵盖多种法律课程和学位级别,旨在评估大语言模型在长文本法律推理中的挑战与性能。

Comments Accepted to ICLR 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.16804 2026-04-03 cs.CV

InTraGen: Trajectory-controlled Video Generation for Object Interactions

InTraGen:基于轨迹的视频生成用于物体交互

Zuhao Liu, Aleksandar Yanev, Ahmad Mahmood, Ivan Nikolov, Saman Motamed, Wei-Shi Zheng, Xi Wang, Lei Sun, Luc Van Gool, Danda Pani Paudel

机构 * ETH Zurich(苏黎世联邦理工学院) Sun Yat-sen University(中山大学) Aalborg University(奥尔堡大学)

AI总结 本文提出InTraGen,通过引入四个新数据集和轨迹质量度量指标,改进多物体交互场景的轨迹引导视频生成,提升视觉真实性和定量性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.01213 2026-04-02 cs.RO cs.MA

Collaborative Task and Path Planning for Heterogeneous Robotic Teams using Multi-Agent PPO

异构机器人团队协同任务与路径规划的多智能体PPO方法

Matthias Rubio, Julia Richter, Hendrik Kolvenbach, Marco Hutter

机构 * Robotic Systems Lab (RSL), ETH Zürich(苏黎世联邦理工学院机器人系统实验室(RSL))

AI总结 本文提出基于多智能体PPO的协同规划策略,用于解决复杂的目标分配与调度问题,通过对比穷举搜索得到的单目标最优解,评估其在行星探索场景中的在线重规划能力。

Comments 8 pages, 3 figures, associated code on https://github.com/leggedrobotics/multi_robot_global_planner

详情

展开后加载摘要…

URL PDF HTML 收藏