14 December 2023

ELLIS Pre-NeurIPS Fest 2023 across Units: The ELLIS Institute Tübingen hosts the event for the Unit Tübingen

Thumb ticker xxl maincover article3

11 ELLIS Units across Europe, a total of 230 posters presented, 152 NeurIPS posters, and about 900 participants. Numerous lively discussions about the latest cutting-edge AI research in the run up to the NeurIPS conference taking place in New Orleans (USA) this week - one of the most important annual events for the global machine learning community - ELLIS units across Europe organized poster sessions to showcase and discuss conference contributions from the ELLIS network and the units’ local research environments.


ELLIS units connect outstanding AI researchers at a certain location and fulfill a set of strict criteria to ensure scientific excellence. Getting a paper accepted at the NeurIPS conference is an important recognition for any scientist in the field of machine learning. To warm up for the event in New Orleans and to foster exchange among peers, members of 11 ELLIS units in different countries presented their NeurIPS contributions during poster sessions in the week before the conference. Scientists from the units’ local research environments were invited to participate with posters as well which provided an opportunity for networking and numerous fruitful discussions.


Event at the ELLIS Unit Tübingen

On December 5, the ELLIS Institute Tübingen hosted the "Tübingen Pre-NeurIPS Fest", a poster session that showcased the NeurIPS contributions of scientists working in the Tübingen AI community. The event was organised jointly with the Tübingen AI Center and the Cluster of Excellence “Machine Learning - New Perspectives for Science.

All the posters presented had one or more ELLIS members as authors. See also the list of the posters presented at the event, with the ELLIS members highlighted in the list of authors.


Poster Title

List of Authors (ELLIS members in bold)

Causal Component Analysis

Liang Wendong, Armin Kekić, Julius von Kügelgen, Simon Buchholz, Michel Besserve, Luigi Gresele, Bernhard Schölkopf

Regularity as Intrinsic Reward for Free Play

Cansu Sancaktar, Justus Piater, Georg Martius

Beyond Average Return in Markov Decision Processes

Alexandre Marthe, Aurélien Garivier, Claire Vernade

Reinforcement Learning with Simple Sequence Priors

Tankred Saanum, Noemi Elteto, Peter Dayan, Marcel Binz, Eric Schulz

RDumb: A simple approach that questions our progress in continual test-time adaptation

Ori Press, Steffen Schneider, Matthias Kümmerer, Matthias Bethge

Online Learning under Adversarial Nonlinear Constraints

Pavel Kolev, Georg Martius, Michael Muehlebach

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius

Compositional Generalization from First Principles

Thaddäus Wiedemer, Prasanna Mayilvahanan, Matthias Bethge, Wieland Brendel

Scale Alone Does not Improve Mechanistic Interpretability

Roland S. Zimmermann, Thomas Klein, Wieland Brendel

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Zeju Qiu, Weiyang Liu, Haiwen Feng, Yuxuan Xue, Yao Feng, Zhen Liu, Dan Zhang, Adrian Weller, Bernhard Schölkopf

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

Leonard Salewski, Isabel Rio-Torto, Stephan Alaniz, Eric Schulz, Zeynep Akata

Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images

Yuxin Wen, John Kirchenbauer, Jonas Geiping, Tom Goldstein

SE(3) Equivariant Augmented Coupling Flows

Laurence Midgley, Vincent Stimper, Javier Antorán, Emile Mathieu, Bernhard Schölkopf, José Miguel Hernández-Lobato

Modulated Neural ODEs

Ilze Amanda Auzina, Çağatay Yıldız, Sara Magliacane, Matthias Bethge, Efstratios Gavves

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

Richard Gao, Michael Deistler, Jakob H Macke

Flow Matching for Scalable Simulation-Based Inference

Maximilian Dax, Jonas Wildberger, Simon Buchholz, Stephen R. Green, Jakob H. Macke, Bernhard Schölkopf

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

Michael Kirchhof, Bálint Mucsányi, Seong Joon Oh, Enkelejda Kasneci


  • More details about the 11 ELLIS units participating at the ELLIS Pre-NeurIPS FEST 2023 with pictures and full list of posters here.
  • More details about the Tuebingen AI Center contributions here.