BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:EPFL Pre-NeurIPS 2026 Poster Session
DTSTART:20261202T163000
DTEND:20261202T190000
DTSTAMP:20261109T164846Z
UID:81add76a245786c41937692e62c5cba4d7571b1824745ca1f11f3e82
CATEGORIES:Conferences - Seminars
DESCRIPTION:The ELLIS Lausanne Unit and the EPFL AI Center are pleased to 
 host the EPFL Pre-NeurIPS 2026 Poster Session\, an informal research gathe
 ring showcasing recent contributions from the EPFL community to NeurIPS 20
 26 and other leading AI and machine learning conferences and workshops.\n\
 nThis event offers an opportunity to discover recent research from across 
 EPFL's AI and machine learning community\, exchange ideas\, and connect wi
 th fellow researchers ahead of NeurIPS 2026. EPFL researchers will also ha
 ve the opportunity to present their latest work during the poster session.
 \n\nRegistration is required to attend the event. Attendance is open to al
 l interested participants.\n\nPoster presentations are reserved for work w
 ith at least one EPFL-affiliated author: [Register and submit your poster
  HERE]\n\nThe session will primarily feature research accepted to NeurIPS 
 2026\, with priority given to:\n\n	NeurIPS 2026 main conference papers\, i
 ncluding Oral and Spotlight presentations\n	NeurIPS 2026 Evaluations & Dat
 asets Track papers\n	NeurIPS 2026 workshop papers\n	Other recent peer-revi
 ewed papers from leading AI and machine learning conferences and workshops
 \, subject to space availability\n\nPoster presenters will be responsible 
 for printing their poster and bringing it to the venue. The session will 
 provide an informal and welcoming setting to share research findings\, eng
 age in discussions\, explore potential collaborations\, and network over s
 nacks\, coffee\, and refreshments.\n\nConfirmed posters (updated on a roll
 ing basis)\nThe list of confirmed posters and presenters will be published
  and updated regularly as registrations are received.\n\nProgramme\n16:00
 –16:30 — Arrival & Poster Set-up\n16:30–19:00 — Poster Session & N
 etworking\n19:00 — Wrap-up\n\nThe list of confirmed posters below is upd
 ated on a rolling basis.\n\n\n	"Beyond Accuracy: A Diagnostic Benchmark fo
 r Hypothesis-Driven Experiment Planning in LLM Agents" - Ryo Kuroki\, Amin
  Mansouri\, Philippe Schwaller\n	"Matchability-Aware Conformal Prediction 
 for Open-Ended Language Model Generation" - Ilia Azizi\n	"Sequence-to-Sequ
 ence Multi-view Stereo" - Aoxiang Fan\, Corentin Dumery\, Nicolas Talabot\
 , Pascal Fua\n	"Stabilizing Extrapolation in Looped Transformers via Learn
 ed Stochastic Stopping" - Hsun-Yu Kuo\, El Mahdi Chayti\, Patrik Reizinge
 r\, Wieland Brendel\, Martin Jaggi\n	"Your Neighbors Know: Leveraging Loca
 l Neighborhoods for Backdoor Detection in Decentralized Learning" - Sayan
  Biswas\, Antoine Boutet\, Davide Frey\, Romaric Gaudel\, Rachid Guerraoui
 \, Maxime Jacovella\, Anne-Marie Kermarrec\, Dimitri Lerévérend\, Franç
 ois Taïani\, Martijn de Vos\n	"MIAM: Modality Imbalance-Aware Masking for
  Multimodal Ecological Applications" - Robin Zbinden\, Wesley Monteith-Fi
 nas\, Gencer Sumbul\, Nina van Tiel\, Chiara Vanalli\, Devis Tuia\n	"Gradi
 ent Descent’s Last Iterate is Often (slightly) Suboptimal" - Guy Kornow
 ski\, Ohad Shamir\n	"Graph Matching Relaxations and Amortization for Super
 vised Graph Prediction" - Federico Méndez\, Paul Krzakala\, Gabriel Melo
 \, Charlotte Laclau\, Rémi Flamary\, Florence d’Alché-Buc\n	"Learning 
 Lean Feedback for Efficient Proof-Candidate Evaluation on GPUs" - Lazar M
 ilikic\, Etienne Bamas\, Emmanuel Abbe\, Viktor Kunčak\n	"Stable and Scal
 able Probabilistic Numerical Solvers for Stiff and High-Dimensional ODEs" 
 - Nathanael Bosch\n	"Euclidean Fourier Neural Operators" - Nathanael Bos
 ch\, Niklas Frederik Schmitz\, Michael F Herbst\n	"Deep Learning as Neural
  Low-Degree Filtering: A Spectral Theory of Hierarchical Feature Learning"
  - Yatin Dandi\, Matteo Vilucchio\, Luca Arnaboldi\, Hugo Tabanelli\, Flo
 rent Krzakala\n	"Geometric Latent Reasoning Induces Shorter Generations in
  LLMs" - Shashi Kumar*\, Yacouba Kaloga*\, Petr Motlicek\, Ina Kodrasi\, 
 Andrea Cavallaro\n\n
LOCATION:MED 0 94.22 https://plan.epfl.ch/?room==MED%200%2094.22
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR