ELLIS Posters

71 accepted poster submissions.

Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks

Emanuel Sommer, Jakob Robnik, Giorgi Nozadze, Uros Seljak, David Rügamer

International Conference on Learning Representations (ICLR) 2025
Presented by: David Rügamer
Multilingual Pretraining for Pixel Language Models

Ilker Kesen, Jonas F. Lotz, Ingo Ziegler, Phillip Rust, Desmond Elliott

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Ilker Kesen
Systems with Switching Causal Relations: A Meta-Causal Perspective

Moritz Willig, Tim Woydt, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting

International Conference on Learning Representations (ICLR) 2025
Presented by: Tim Woydt
QuEST: Stable Training of LLMs with 1-Bit Weights and Activations

Andrei Panferov, Jiale Chen, Soroush Tabesh, Mahdi Nikdan, Dan Alistarh

International Conference on Machine Learning (ICML) 2025
Presented by: Andrei Panferov
On Space Folds of Neural Networks

Michal Lewandowski, Hamid Egbalzadeh, Bernhard Heinzl, Raphael Pisoni, Bernhard A.Moser

Transactions of Machine Learning Research (TMLR)
Presented by: Michal Lewandowski
DiTASK: Multi-Task Fine-Tuning with Diffeomorphic Transformations

Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Bruno Ribeiro, Chaim Baskin, Moshe Eliasof

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Krishna Sri Ipsit Mantri
On the Low-Rank Parametrization of Reward Models for Controlled Language Generation

Sergey Troshin, Vlad Niculae, Antske Fokkens

Transactions of Machine Learning Research (TMLR)
Presented by: Sergey Troshin
Keep your distance: learning dispersed embeddings on Sm

Evgeniia Tokarchuk, Hua Chang Bakker, Vlad Niculae

Transactions of Machine Learning Research (TMLR)
Presented by: Evgeniia Tokarchuk
ASTrA: Adversarial Self-supervised Training with Adaptive-Attacks

Prakash Chandra Chhipa, Gautam Vashishtha, Settur Jithamanyu, Rajkumar Saini, Mubarak Shah, Marcus Liwicki

International Conference on Learning Representations (ICLR) 2025
Presented by: Prakash Chandra Chhipa
Cost-aware simulation-based inference

Ayush Bharti, Daolang Huang, Samuel Kaski, Francois-Xavier Briol

Artificial Intelligence and Statistics (AISTATS) 2025
Presented by: Ayush Bharti
Recent advances in likelihood-free Bayesian inference and its applications

There are too many, we want to make a combined poster from multiple highlight papers on the indicated theme

Journal of Machine Learning Research (JMLR)
Presented by: Jukka Corander
Paths and Ambient Spaces in Neural Loss Landscapes

Daniel Dold, Julius Kobialka, Nicolai Palm, Emanuel Sommer, David Rügamer, Oliver Dürr

Artificial Intelligence and Statistics (AISTATS) 2025
Presented by: Julius Kobialka
Gradient Extrapolation for Debiased Representation Learning

Ihab Asaad, Maha Shadaydeh, Joachim Denzler

International Conference on Computer Vision (ICCV) 2025
Presented by: Ihab Asaad
On convex decision regions in deep network representations

Lenka Tětková, Thea Brüsch, Teresa Dorszewski, Fabian Martin Mager, Rasmus Ørtoft Aagaard, Jonathan Foldager, Tommy Sonne Alstrøm, Lars Kai Hansen

Nature Communications
Presented by: Lenka Tětková
Density Ratio Estimation with Conditional Probability Paths

Hanlin Yu, Arto Klami, Aapo Hyvärinen, Anna Korba, Omar Chehab

International Conference on Machine Learning (ICML) 2025
Presented by: Hanlin Yu
An Efficient Search-and-Score Algorithm for Ancestral Graphs using Multivariate Information Scores for Complex Non-linear and Categorical Data

Nikita Lagrange, Hervé Isambert

International Conference on Machine Learning (ICML) 2025
Presented by: Nikita Lagrange
Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization

Yu-Han Wu, Pierre Marion, Gérard Biau, Claire Boyer

Annual Conference on Learning Theory (COLT) 2025
Presented by: Pierre Marion
SFESS: Score Function Estimators for k-Subset Sampling

Klas Wijk, Ricardo Vinuesa, Hossein Azizpour

International Conference on Learning Representations (ICLR) 2025
Presented by: Klas Wijk
Safe-EF: Error Feedback for Nonsmooth Constrained Optimization

Rustem Islamov, Yarden As, Ilyas Fatkhullin

International Conference on Machine Learning (ICML) 2025
Presented by: Rustem Islamov
Efficient Open Set Single Image Test Time Adaptation of Vision Language Models

Manogna Sreenivas, Soma Biswas

Transactions of Machine Learning Research (TMLR)
Presented by: Manogna Sreenivas
Discriminative Ordering Through Ensemble Consensus

Louis Ohl, Fredrik Lindsten

Conference on Uncertainty in Artificial Intelligence (UAI) 2025
Presented by: Louis Ohl
SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation

Hai Pham, Tung Do, Phong Nguyen, Binh-Son Hua, Khoi Nguyen, Rang Nguyen

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Hai Pham
ColonScopeX: Leveraging Explainable Expert Systems with Multimodal Data for Improved Early Diagnosis of Colorectal Cancer

Natalia Sikora, Robert L. Manschke, Alethea M. Tang, Peter Dunstan, Dean A. Harris, Su Yang

AAAI-25 B1: AI for Medicine and Healthcare
Presented by: Natalia Sikora
SEKE: Specialised Experts for Keyword Extraction

Matej Martinc ~Matej_Martinc1 , Thi Hong Hanh TRAN, Senja Pollak, Boshko Koloski

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Boshko Koloski
How Redundant Is the Transformer Stack in Speech Representation Models?

Teresa Dorszewski, Albert Kjøller Jacobsen, Lenka Tětková, and Lars Kai Hansen

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2025
Presented by: Albert Kjøller Jacobsen
Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

Niklas Schmidinger ~Niklas_Schmidinger1 , Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek, Pieter-Jan Hoedt, Johannes Brandstetter, Andreas Mayr, Sohvi Luukkonen, Sepp Hochreiter, Günter Klambauer

International Conference on Learning Representations (ICLR) 2025
Presented by: Sohvi Luukkonen
A unifying framework for generalised Bayesian online learning in non-stationary environments

Gerardo Duran-Martin, Leandro Sánchez-Betancourt, Alex Shestopaloff, Kevin Patrick Murphy

Transactions of Machine Learning Research (TMLR)
Presented by: Gerardo Duran-Martin
Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption

Audrey Poinsot, Panayiotis Panayiotou, Alessandro Leite, Nicolas Chesneau, Özgür Simsek, Marc Schoenauer

International Conference on Machine Learning (ICML) 2025
Presented by: Audrey Poinsot
Improved Variational Inference in Discrete VAEs using Error Correcting Codes

María Martínez-García, Grace Villacrés, David Mitchell, Pablo M. Olmos

Conference on Uncertainty in Artificial Intelligence (UAI) 2025
Presented by: Pablo M. Olmos
The art of deception: Color visual illusions and diffusion models

Alexandra Gomez-Villa, Kai Wang, C Alejandro Parraga, Bartłomiej Twardowski, Jesus Malo, Javier Vazquez-Corral, Joost van den Weijer

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Alexandra Gomez-Villa
ELBOing Stein: Variational bayes with Stein mixture inference

Ola Rønning; Eric Nalisnick; Christophe Ley; Padhraic Smyth; Thomas Hamelryck

International Conference on Learning Representations (ICLR) 2025
Presented by: Ola Rønning
GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks

Taraneh Younesian ~Taraneh_Younesian2 , Daniel Daza, Emile van Krieken, Thiviyan Thanapalasingam, Peter Bloem

Transactions of Machine Learning Research (TMLR)
Presented by: Emile van Krieken
Energy-Based Flow Matching for Generating 3D Molecular Structure

Wenyin Zhou, Christopher Iliffe Sprague, Vsevolod Viliuga, Matteo Tadiello, Arne Elofsson, Hossein Azizpour

International Conference on Machine Learning (ICML) 2025
Presented by: Wenyin Zhou
Prediction hubs are context-informed frequent tokens in LLMs

Beatrix MG Nielsen, Iuri Macocco, Marco Baroni

Annual Meeting of the Association for Computational Linguistics (ACL) 2025
Presented by: Beatrix M. G. Nielsen
Limits to scalable evaluation at the frontier: LLM as judge won’t beat twice the data

Florian E. Dorner, Vivian Nastl, Moritz Hardt

International Conference on Learning Representations (ICLR) 2025
Presented by: Vivian Nastl
How to safely discard features based on aggregate SHAP values

Robi Bhattacharjee, Karolin Frohnapfel, Ulrike von Luxburg

Annual Conference on Learning Theory (COLT) 2025
Presented by: Karolin Frohnapfel
All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling

Emanuele Marconato, Sébastien Lachapelle, Sebastian Weichwald, Luigi Gresele

Artificial Intelligence and Statistics (AISTATS) 2025
Presented by: Luigi Gresele
Disentangling Interactions and Dependencies in Feature Attribution

Gunnar König, Eric Günther, Ulrike von Luxburg

Artificial Intelligence and Statistics (AISTATS) 2025
Presented by: Eric Günther
Numerically Robust Fixed-Point Smoothing Without State Augmentation

Nicholas Krämer

Transactions of Machine Learning Research (TMLR)
Presented by: Nicholas Krämer
A Model Zoo on Phase Transitions in Neural Networks

Konstantin Schürholt, Léo Meynent, Yefan Zhou, Haiquan Lu, Yaoqing Yang, Damian Borth

Journal of Data-centric Machine Learning Research (DMLR)
Presented by: Léo Meynent
Can LLMs Separate Instructions From Data? And What Do We Even Mean By That?

Egor Zverev, Sahar Abdelnabi, Soroush Tabesh, Mario Fritz, Christoph H Lampert

International Conference on Learning Representations (ICLR) 2025
Presented by: Egor Zverev
Identifying Metric Structures of Deep Latent Variable Models

Stas Syrota, Yevgen Zainchkovskyy, Johnny Xi, Benjamin Bloem-Reddy, Søren Hauberg

ICML
Presented by: Stas Syrota
Unstructured Evidence Attribution for Long Context Query Focused Summarization

Dustin Wright , Zain Muhammad Mujahid, Lu Wang, Isabelle Augenstein, David Jurgens

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Dustin Wright
Efficient Knowledge Injection in LLMs via Self-Distillation

Kalle Kujanpää, Pekka Marttinen, Harri Valpola, Alexander Ilin

Transactions of Machine Learning Research (TMLR)
Presented by: Pekka Marttinen
How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination

Saad Obaid Ul Islam, Anne Lauscher, Goran Glavaš

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Saad Obaid ul Islam
TinyFoA: Memory Efficient Forward-Only Algorithm for On-Device Learning

Baichuan Huang, Amir Aminifar

AAAI Conference on Artificial Intelligence (AAAI) 2025
Presented by: Baichuan Huang
The Impact of Inference Acceleration on Bias of LLMs

Elisabeth Kirsten, Ivan Habernal, Vedant Nanda, Muhammad Bilal Zafar

Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics (NAACL) 2025
Presented by: Elisabeth Kirsten
Multi-Modal Framing Analysis of News

Arnav Arora, Srishti Yadav, Maria Antoniak, Serge Belongie, Isabelle Augenstein

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Arnav Arora
From Sound to Sight: Towards AI-authored Music Videos

Leo Vitasovic, Stella Graßhof, Agnes Mercedes Kloft, Ville V. Lehtola, Martin Cunneen, Justyna Starostka, Glenn McGarry, Kun Li, Sami S. Brandt

International Conference on Computer Vision (ICCV) 2025
Presented by: Leo Vitasovic
Archetypal Analysis for Binary Data

A. Emilie J. Wedenborg, Morten Mørup

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)
Presented by: Emilie Wedenborg
S2WTM: Spherical Sliced-Wasserstein Autoencoder for Topic Modeling

Suman Adhya, Debarshi Kumar Sanyal

Annual Meeting of the Association for Computational Linguistics (ACL) 2025
Presented by: Suman Adhya
Relational Conformal Prediction for Correlated Time Series

Andrea Cini, Alexander Jenkins, Danilo Mandic, Cesare Alippi, Filippo Maria Bianchi

International Conference on Machine Learning (ICML) 2025
Presented by: Andrea Cini
Zero-shot Imputation with Foundation Inference Models for Dynamical Systems

Patrick Seifner, Kostadin Cvejoski, Antonia Körner, Ramses Sanchez

International Conference on Learning Representations (ICLR) 2025
Presented by: Ramses Sanchez
MaxCutPool: differentiable feature-aware Maxcut for pooling in graph neural networks

Carlo Abate, Filippo Maria Bianchi

International Conference on Learning Representations (ICLR) 2025
Presented by: Carlo Abate
CodeSSM: Towards State Space Models for Code Understanding

Shweta Verma, Abhinav Anand, Mira Mezini

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Abhinav Anand
Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering

Evelyn D'Elia, Paolo Maria Viceconte, Lorenzo Rapetti, Diego Ferigo, Giulio Romualdi, Giuseppe L'Erario, Raffaello Camoriano, Daniele Pucci

International Conference on Intelligent Robots and Systems (IROS) 2025
Presented by: Raffaello Camoriano
No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces

Daniel Marczak, Simone Magistri, Sebastian Cygert, Bartłomiej Twardowski, Andrew D. Bagdanov, Joost van de Weijer

International Conference on Machine Learning (ICML) 2025
Presented by: Simone Magistri
TimeMixer++: A General Time Series Pattern Machine for Universal Predictive Analysis

Shiyu Wang, Jiawei Li, Xiaoming Shi, Zhou Ye, Baichuan Mo, Wenze Lin, Shengtong Ju, Zhixuan Chu, Ming Jin

International Conference on Learning Representations (ICLR) 2025
Presented by: Jiawei Li
Image Generation Diversity Issues and How to Tame Them

Mischa Dombrowski; Weitong Zhang; Sarah Cechnicka; Hadrien Reynaud; Bernhard Kainz

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Mischa Dombrowski
Echoes of Agreement: Argument driven opinion shifts in Large Language models

Avneet Kaur

Empirical Methods in Natural Language Processing (EMNLP) 2025
Presented by: Avneet Kaur
Video-Language Critic: Transferable Reward Functions for Language-Conditioned Robotics

Minttu Alakuijala, Reginald McLean, Isaac Woungang, Nariman Farsad, Samuel Kaski, Pekka Marttinen, Kai Yuan

Transactions of Machine Learning Research (TMLR)
Presented by: Minttu Alakuijala
Pre-Forgettable Models: Prompt Learning as a Native Mechanism for Unlearning

Rutger Hendrix, Giovanni Patanè, Leonardo G Russo, Simone Carnemolla, Giovanni Bellitto, Federica Proietto Salanitri, Concetto Spampinato, Matteo Pennisi

ACM Multimedia 2025
Presented by: Matteo Pennisi
Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models

Jinhui Yi, Syed Talal Wasim, Yanan Luo, Muzammal Naseer, Juergen Gall

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Yanan Luo
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

Syed Talal Wasim, Hamid Suleman, Olga Zatsarynna, Muzammal Naseer, Juergen Gall

International Conference on Computer Vision (ICCV) 2025
Presented by: Syed Talal Wasim
Multi-Hop Reasoning for Question Answering with Hyperbolic Representations

Simon Welz, Lucie Flek, Akbar Karimi

Annual Meeting of the Association for Computational Linguistics (ACL) 2025
Presented by: Akbar Karimi
Understanding the sources of performance in deep drug response models reveals insights and improvements

Nikhil Branson, Pedro R Cutillas, Conrad Bessant

Bioinformatics, (oral/proceedings ISMB/ECCB 2025 18% acceptance rate
Presented by: Nikhil Branson
SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction

Enrico Pallotta, Sina Mokhtarzadeh Azar, Shuai Li, Olga Zatsarynna, Jürgen Gall

Computer Vision and Pattern Recognition (CVPR) 2025
Presented by: Sina Mokhtarzadeh Azar
MixANT: Observation-dependent Memory Propagation for Stochastic Dense Action Anticipation

Syed Talal Wasim, Hamid Suleman, Olga Zatsarynna, Muzammal Naseer, Juergen Gall

International Conference on Computer Vision (ICCV) 2025
Presented by: Hamid Suleman
REPEAT: improving uncertainty estimation in representation learning explainability

Kristoffer K. Wickstrøm, Thea Brüsch, Michael C. Kampffmeyer, Robert Jenssen

AAAI Conference on Artificial Intelligence (AAAI) 2025
Presented by: Kristoffer Wickstrøm
Capturing Temporal Dynamics in Large-Scale Canopy Tree Height Estimation

Jan Pauls, Max Zimmer, Berkant Turan, Sassan Saatchi, Philippe Ciais, Sebastian Pokutta, Fabian Gieseke

International Conference on Machine Learning (ICML) 2025
Presented by: Jan Pauls
Start Smart: Leveraging Gradients For Enhancing Mask-based XAI Methods

Buelent Uendes, Shujian Yu, Mark Hoogendoorn

International Conference on Learning Representations (ICLR) 2025
Presented by: Buelent Uendes