Celebrating the most cutting-edge machine learning research of the Amsterdam AI Ecosystem

Come and join us at the preview party of the research papers published at top-tier conferences in machine learning, and network with the vibrant AI ecosystem here in Amsterdam!
Date: Thursday, June 8th, 2023
Time: 16:00 –19:30 CET
Location: Lab42, Amsterdam


16:00-16:10: Welcome remark by Prof. dr. Cees G.M. Snoek, Director of ELLIS unit Amsterdam (venue: L1.02)
16:10-17:00: Keynote presentation by Jakub Tomczak, Associate Professor PI of Generative AI Group, Eindhoven University of Technology (venue: L1.02)
17.00-19.30: Poster presentation accompanied with light refreshment (venue: ground floor)

Keynote speaker

Is there a place for Representation Learning in Generative AI?
Deep Learning, Representation Learning, and Generative AI. These are three buzzwords that appear not only in research papers but also newspapers and social media. However, how are these three concepts related to each other? Generative AI is built on top of the success of Deep Learning, but is there a place for Representation Learning? This talk aims at entertaining the audience with a brief introduction to Generative AI and Representation Learning, and at indicating a possible way of marrying these two fields.

Jakub M. Tomczak is an associate professor at the Eindhoven University of Technology (TU/e). Before joining the TU/e, he was an assistant professor of Artificial Intelligence at Vrije Universiteit Amsterdam. Formerly, he was a deep learning researcher (Engineer, Staff) in Qualcomm AI Research in Amsterdam, a Marie Sklodowska-Curie individual fellow in Prof. Max Welling’s group at the University of Amsterdam, and an assistant professor and a postdoc at the Wroclaw University of Technology. His main research interests include deep generative modeling, deep learning, and Bayesian inference, with applications to image processing, life sciences & chemistry, and medicine. He is the author of the book entitled “Deep Generative Modeling”. He has broad experience in consulting companies in logistics, banking, computer vision, and life sciences. He has over 12 years of experience working in academia and over 3 years working in and for the industry.

Posters showcased at the event

Reducing Predictive Feature Suppression in Resource-Constrained Contrastive Image-Caption Retrieval
Andrew Yates · Maarten de Rijke · Maurits Bleeker  
Published at the Transactions on Machine Learning Research (TMLR) 2023
BISCUIT: Causal Representation Learning from Binary Interactions
Sara Magliacane · Sindy Löwe · Yuki M. Asano · Taco Cohen · Efstratios Gavves · Philipp Lippe 
Published at the Conference on Uncertainty in Artificial Intelligence (UAI) 2023
Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems
Sara Magliacane · Sindy Löwe · Yuki M. Asano· Taco Cohen · Efstratios Gavves· Philipp Lippe  
Published at the International Conference on Learning Representation (ICLR) 2023
Rigid body flows for sampling molecular crystal structures

Pim de Haan · Jonas Köhler · Michele Invernizzi · Frank Noe 


Published at the International Conference on Machine Learning (ICML) 2023

Injecting the BM25 Score as Text Improves BERT-Based Re-rankers

Arian Askari  · Amin Abolghasemi  ·  Gabriella Pasi  · Wessel Kraaij  · Suzan Verberne

Published at the European Conference on Information Retrieval (ECIR) 2023

sigmoidF1: A Smooth F1 Score Surrogate Loss for Multilabel Classification


Gabriel Bénédict · Hendrik Vincent Koops · Daan Odijk · Maarten de Rijke 

 Published at the TMLR 2023

An Offline Metric for the Debiasedness of Click Models


Romain Deffayet  · Jean-Michel Renders  ·  Maarten de Rijke  · Philipp Hager  


 Published at the SIGIR 2023

Test of Time: Instilling Video-Language Models with a Sense of Time
Piyush Bagad · Makarand Tapaswi · Cees Snoek
Published at  the Computer Vision and Pattern Recognition (CVPR) 2023
Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization

Harrie Oosterhuis · Maarten de Rijke · Shashank Gupta 


Published at the SIGIR 2023

Self-Guided Diffusion Models
Vincent Tao Hu* · David W Zhang* ·  Yuki M. Asano ·  Gertjan J. Burghouts ·  Cees Snoek


Published at  the CVPR 2023

Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning

Xiantong Zhen · Marcel Worring ·  Ivona Najdenkoska


Published at the ICLR 2023

Graph Switching Dynamical Systems

Yongtuo Liu · Sara Magliacane · Miltiadis (Miltos) Kofinas · Efstratios Gavves


Published at the ICML 2023

Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model 

Yeskendir Koishekenov · Alexandre Berard · Vassilina Nikoulina

 Published at the Association for Computational Linguistics (ACL) 2023

E(n) Equivariant Message Passing Simplicial Networks 


Floor Eijkelboom ·  Rob Hesselink ·  Erik Bekkers


Published at the ICML 2023

Scene-centric vs. Object-centric Image-Text Cross-modal Retrieval: A Reproducibility Study 

Mariya Hendriksen · Svitlana Vakulenko · Ernst Kuiper ·  Maarten de Rijke


Published at the ECIR 2023

3D Human Pose Estimation via Intuitive Physics 


Shashank Tripathi · Lea Müller ·  Chun-Hao Paul Huang · Omid Taheri ·  Michael J. Black · Dimitrios Tzionas

Published at the CVPR 2023
Balancing Fairness and Efficiency in Transport Network Design through Reinforcement Learning 

Dimitris Michailidis · Sennay Ghebreab · Fernando P. Santos 


Published at the International Conference on Autonomous Agents and Multiagent Systems (AAMAS) 2023

Multi-objective optimization via equivariant deep hypervolume approximation 


Jim Boelrijk · Bernd Ensing · Patrick Forré


Published at the ICLR 2023

Interpretable Word Sense Representations via Definition Generation: The Case of Semantic Change Analysis 

Mario Giulianelli · Iris Luden · Raquel Fernández · Andrey Kutuzov 


Published at the ACL 2023

SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail
Yingjun Du ·  Jiayi Shen · Xiantong Zhen ·  Cees G. M. Snoek

Published at the CVPR 2023

MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks

Wenfang Sun · Yingjun Du · Xiantong Zhen · Fan Wang · Ling Wang · Cees G.M. Snoek 


Published at the ICML 2023

Speaking the Language of Your Listener: Audience-Aware Adaptation via Plug-and-Play Theory of Mind

Ece Takmaz* · Nicolo’ Brandizzi* ·  Mario Giulianelli · Sandro Pezzelle·  Raquel Fernández 

* Shared first authorship
 Published at the Findings of ACL 2023
MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering

Andrew Yates · Evangelos Kanoulas ·  Maarten de Rijke ·  Vaishali Pal


Published at the ACL 2023

A Unified Generative Retriever for Knowledge-Intensive Language Tasks via Prompt Learning 

Jiangui Chen · Ruqing Zhang · Jiafeng Guo · Maarten de Rijke · Yiqun Liu, Yixing Fan ·  Xueqi Cheng

Published at the SIGIR 2023
Tailed U-net Multi-scale Music Representation Learning

John Ashley Burgoyne · Marcel Velez



Published at the International Society for Music Information Retrieval (ISMIR) 2023

Modelling Long Range Dependencies in N-D: From Task-Specific to a General Purpose CNN
David M Knigge · David W. Romero ·  Albert Gu · Efstratios Gavves · Erik J Bekkers ·  Jakub Mikolaj Tomczak · Mark Hoogendoorn ·  Jan-jakob Sonke
Published at the ICLR 2023
Uncertainty-Aware Multiple-Instance Learning for Reliable Classification: Application to Optical Coherence Tomography

Coen de Vente · Bram van Ginneken · Carel B. Hoyng · Caroline C.W. Klaver · Clara I. Sánchez

Under review 

Unlocking Slot Attention by Changing Optimal Transport Costs 

Yan Zhang* · David W. Zhang* ·  Simon Lacoste-Julien ·  Gertjan J. Burghouts · Cees G. M. Snoek


Published at the ICML 2023
The Deep Learning Extravaganza is organized by ELLIS unit Amsterdam, in collaboration with the Deep Thinking Hour.