BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:EPFL Pre-ICML 2026 Poster Session
DTSTART:20260629T163000
DTEND:20260629T190000
DTSTAMP:20260921T135225Z
UID:e4c8d3c8e442175b20ad9e938004f47a7d324800e204fb75cb41b834
CATEGORIES:Conferences - Seminars
DESCRIPTION:The ELLIS Lausanne Unit and the EPFL AI Center are pleased to 
 host the EPFL Pre-ICML 2026 Poster Session\, an informal research gatherin
 g highlighting recent contributions from the EPFL community to ICML 2026 a
 nd other leading machine learning conferences and workshops.\n\nThis poste
 r session is a great opportunity for researchers to showcase their work\, 
 discover ongoing projects across EPFL’s machine learning ecosystem\, and
  connect with fellow researchers ahead of ICML.\n\nRegistration required\,
  present your poster: HERE (list of confirmed posters is provided below)\
 n\nThe session will primarily feature posters of papers accepted to ICML 2
 026. Priority will be given to:\n\n	ICML 2026 conference papers\n	ICML 202
 6 workshop papers\n	Other peer-reviewed papers from major machine learning
  conferences and workshops\, subject to space availability\n\nThe session 
 is to provide an informal setting for presenting posters\, exchanging idea
 s\, and networking over snacks\, coffee\, and refreshments.\n\nConfirmed p
 osters (updated on a rolling basis)\n\n\n	“A solvable high-dimensional m
 odel where nonlinear autoencoders learn structure invisible to PCA while t
 est loss misaligns with generalization”\, Vicente Conde Mendes∗ \, Lor
 enzo Bardone∗ \, Cedric Koller* \, Jorge Medina Moreira∗ \, Vittorio E
 rba\, Emanuele Troiani\, Lenka Zdeborova\n	“Single-Head Attention in Hig
 h Dimensions: A Theory of Generalization\, Weights Spectra\, and Scaling L
 aws”\, Fabrizio Boncoraglio\, Vittorio Erba\, Emanuele Troiani\, Yizhou 
 Xu\, Lenka Zdeborová\, Florent Krzakala\n	“Fixed-Point Masked Generativ
 e Modeling”\, Andrea Miele\, Yiming Qin\, Alba Carballo-Castro\, Justin 
 Deschenaux\, Pascal Frossard\n	“Weight Space Representation Learning via
  Neural Field Adaptation”\, Zhuoqian Yang\, Mathieu Salzmann\, Sabine S
 üsstrunk          \n	“Preference-Based Distributed Welfare Ma
 ximization: A Game-Theoretic Approach”\, Antoine Bergerault\, Anna Maddu
 x\, Andreas Schlaginhaufen\, Maryam Kamgarpour\n	“(1D) Ordered Tokens En
 able Efficient Test-Time Search”\, Zhitong Gao\, Parham Rezaei\, Ali Cy\
 , Mingqiao Ye\, Nataša Jovanović\, Jesse Allardice\, Afshin Dehghan\, Am
 ir Zamir\, Roman Bachmann\, Oğuzhan Fatih Kar              
                  \n	“RECTOR: Masked Region-Channel-Temp
 oral Modeling for Affective and Cognitive Representation Learning”\, Jin
 han Liu\, Mahsa Shoaran\n	"Sparse Neuron Ablation Triggers Catastrophic Co
 llapse  of the Language Core in Vision-Language Models"\, Cen Lu\, Yung-C
 hen Tang\, Andrea Cavallaro \n	"Recursive Scaling in Masked Diffusion Mod
 els Portrait"\, Alba Carballo-Castro\, Julianna Piskorz\, Paulius Rauba\, 
 Mihaela van der Schaar\, Pascal Frossard\n	"Efficient Edge-aware Attention
  Network for Graph Generation"\, Vincent Jung\, Alba Carballo-Castro\, Yim
 ing QIN\, Lonneke van der Plas\, Pascal Frossard\n	"PrivLEX: Detecting leg
 al concepts in images through Vision-Language Models"\, Darya Baranouskaya
 \, Andrea Cavallaro\n	"Why Linear Recurrent Memory Works in Partially Obse
 rvable Reinforcement Learning"\, Yike Zhao\, Onno Eberhard\, Malek Khammas
 si\, Ali H. Sayed\, Michael Muehlebach\n	"Weight Space Representation Lear
 ning via Neural Field Adaptation"\, Zhuoqian Yang\, Mathieu Salzmann\, Sab
 ine Süsstrunk\n	\n	"Time series saliency maps: explaining models across m
 ultiple domains" - Christodoulos Kechris\, Jonathan Dan\, David Atienza\n	
 \n	"Deep networks learn to parse uniform-depth context-free languages from
  local statistics" - Jack T. Parley\, Francesco Cagnetta and Matthieu Wyar
 t\n	"Multi Agent IL"\, Luca Viano\, Freihaut\, Nevali\, Cevher\, Geist and
  Ramponi\n	\n	"DynaVieW: Schema-Guided World Modeling for Understanding Hi
 erarchical Visual Dynamics"\, Silin Gao* \, Hao Zhao*\, Zeming Chen\, Sepi
 deh Mamooler\, Antara Raaghavi Bhattacharya\, Qiyu Wu\, Hiromi Wakaki\, Yu
 ki Mitsufuji\, Li Mi\, Syrielle Montariol\, Antoine Bosselut\n	\n\n\nProgr
 amme\n16:00–16:30 — Arrival & Poster set-up\n16:30–18:30 — Poster 
 Session & Networking\n18:30–19:00 — Wrap-up\n\nThe full list of confir
 med posters and presenters will be shared closer to the event date.\n\nThi
 s event is part of the ELLIS Sites ICML Fest 2026: Celebrate\, Connect\, 
 Collaborate.
LOCATION:ELE 117 https://plan.epfl.ch/?room==ELE%20117
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR