DEEP LEARNING EXTRAVAGANZA
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
Programme
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 BleekerPublished 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 LippePublished 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 LippePublished 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
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
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
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
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
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.
