deep learning extravaganza 2024
The ELLIS unit Amsterdam is proud to announce the Deep Learning Extravaganza in collaboration with the Deep Thinking Hour at Lab42. Attend the event to connect with Amsterdam’s innovators and explore the latest cutting-edge Machine Learning research.
The event will take place on June 13th, 16:00-19:30, at Lab42 (Science Park, University of Amsterdam) and will feature a keynote presentation (16:00-17:00) followed by a poster session with drinks and bites (17:00-19:30). Use this link to sign up to the event.
Megan Stanley, Microsoft Research Lab
Keynote presenter
Aurora, the first large-scale foundation model of the atmosphere
She is a Senior Researcher in the Machine Intelligence group with a focus on methods applied to natural sciences and drug-discovery. Her interests include meta-learning and generative models. She previously completed a PhD at the University of Cambridge at the intersection between Quantum Optics and Condensed Matter.
Below, you will find an overview over the papers that will be presented at the event.
presented papers
The Unreasonable Effectiveness of Random Target Embeddings for Continuous-Output Neural Machine Translation
Evgeniia Tokarchuk · Vlad Niculae
NAACL 2024 (main track)
Clifford-Steerable Convolutional Neural Networks
Maksim Zhdanov · David Ruhe · Maurice Weiler · Ana Lucic · Johannes Brandstetter · Patrick Forré
ICML 2024
Continual hyperbolic learning of instances and classes
Melika Ayoughi · Mina Ghadimiatigh · Mohammad Mehdi Derakhshani · Cees Snoek · Paul Groth · Pascal Mettes
under review (TOMM journal)
DNA: Differentially private Neural Augmentation for contact tracing
Rob Romijnders · Christos Louizos · Yuki M. Asano · Max Welling
ICLR 2024 (Private ML workshop)
Learning Fair Cooperation in Mixed-Motive Games with Indirect Reciprocity
Jacobus Martin Smit · Fernando P. Santos
IJCAI 2024 (main track)
CORE: Towards Scalable and Efficient Causal Discovery with Reinforcement Learning
Andreas W. M. Sauter · Nicolò Botteghi · Erman Acar · Aske Plaat
AAMAS 2024 (main track)
Emergent Cooperation under Uncertain Incentive Alignment
Nicole Orzan · Erman Acar · Davide Grossi · Roxana Rădulescu
AAMAS 2024 (main track)
CausalPlayground: Addressing Data-Generation Requirements in Cutting-Edge Causality Research
Andreas W. M. Sauter · Erman Acar · Aske Plaat
CVPR 2024 (CORR workshop)
Neural Diffusion Models
Grigory Bartosh · Dmitry Vetrov · Christian A. Naesseth
Don’t Buy it! Reassessing the Ad Understanding Abilities of Contrastive Multimodal Models
Anna Bavaresco · Alberto Testoni · Raquel Fernández
ACL 2024 (track: Multimodality and Language Grounding to Vision, Robotics and Beyond)
A Sparsity Principle for Partially Observable Causal Representation Learning
Danru Xu · Dingling Yao · Sébastien Lachapelle · Perouz Taslakian · Julius von Kügelgen · Francesco Locatello · Sara Magliacane
ICML 2024
DIBS: Enhancing Dense Video Captioning with Unlabeled Videos via Pseudo Boundary Enrichment and Online Refinement
Hao Wu · Huabin Liu · Yu Qiao · Xiao Sun
CVPR 2024 (main track)
A Machine with Short-Term, Episodic, and Semantic Memory Systems
Taewoon Kim · Michael Cochez · Vincent François-Lavet · Mark Neerincx · Piek Vossen
AAAI 2023
Any-Shift Prompting for Generalization over Distributions
Zehao Xiao · Jiayi Shen · Mohammad Mahdi Derakhshani · Shengcai Liao · Cees G. M. Snoek
CVPR 2024
Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
Erik Arakelyan · Pasquale Minervini · Daniel Daza · Michael Cochez · Isabelle Augenstein
NeurIPS 2023
How to Train Neural Field Representations: A Comprehensive Study and Benchmark
Samuele Papa · Riccardo Valperga · David Knigge · Miltiadis Kofinas, Phillip Lippe · Jan-Jakob Sonke · Efstratios Gavves
CVPR 2024
Compositional Entailment Learning for Hyperbolic Vision-Language Models
Avik Pal · Max van Spengler · Guido D’Amely · Alessandro Flaborea · Fabio Galasso · Pascal Mettes
VeRA: Vector-based Random Matrix Adaptation
Dawid J. Kopiczko · Tijmen Blankevoort · Yuki M. Asano
ICLR 2024 (main track)
Ai-Sampler: Adversarial Learning of Markov kernels with involutive maps
Evgenii Egorov · Ricardo Valperga · Efstratios Gavves
ICML 2024
A Probabilistic Approach to Learning the Degree of Equivariance in Steerable CNNs
Lars Veefkind · Gabriele Cesa
ICML 2024 (main track)
Learning in Public Goods Games with Non-Linear Utilities: a Multi-Objective Approach
Nicole Orzan · Erman Acar · Davide Grossi · Roxana Radulescu
ALA 2024
CompFuser: Enabling Spatial Composition in Text-to-Image Generation
Mohammad Mahdi Derakhshani · Menglin Xia · Harkirat Behl · Cees GM Snoek · Victor Rühle