NeurIPS Fest 2023

Annual NeurIPS-preview party spotlighting Amsterdam's finest and latest research in machine learning

Come and deep dive into the state-of-the-art machine learning research that will be showcased at the NeurIPS Conference in New Orleans!
Date: Thursday, 7 December 2023
Time: 17:00-20:00
Venue: Lab42


17:00-18:00: Keynote Speaker, Prof. Dr. Juergen Gall, University of Bonn (venue: L1.01)
18:00-20:00: Poster Session with bites and drinks (venue: ground floor)
For logistic purposes, kindly register here (

Keynote speaker

Prof. Dr. Juergen Gall is Professor and Head of the Computer Vision Group at the University of Bonn since 2013, spokesperson of the Transdisciplinary Research Area “Mathematics, Modelling and Simulation of Complex Systems”, and member of the Lamarr Institute for Machine Learning and Artificial Intelligence. After his Ph.D. in computer science from the Saarland University and the Max Planck Institute for Informatics, he was a postdoctoral researcher at the Computer Vision Laboratory, ETH Zurich, from 2009 until 2012 and senior research scientist at the Max Planck Institute for Intelligent Systems in Tübingen from 2012 until 2013. He received a grant for an independent Emmy Noether research group from the German Research Foundation (DFG) in 2013, the German Pattern Recognition Award of the German Association for Pattern Recognition (DAGM) in 2014, an ERC Starting Grant in 2016, and an ERC Consolidator Grant in 2022.

Anticipation: From Human Motion to Wildfires

In this talk, he will give an overview of some recent works on anticipating human motion. In particular, he will discuss Social Diffusion, a diffusion approach for short-term and long-term forecasting of the motion of multiple persons as well as their social interactions. He will also introduce the “Humans in Kitchens” dataset, a new benchmark for multi-person human motion forecasting with scene context. Finally, he will briefly describe an approach for forecasting unintentional actions and, if time permits, he will also discuss how wildfire and agricultural droughts can be forecast.

Posters showcased at the event

Main track papers
Flow Factorized Representation Learning
Yue Song ·  Thomas Anderson Keller  · Nicu Sebe  · Max Welling  
Learning to Learn Prototypical Networks by Task-Guided Diffusion
Yingjun Du · Zehao Xiao · Shencai Liao · Cees Snoek  
Learning Unseen Modality Interaction

Yunhua Zhang   

Implicit Convolutional Kernels for Steerable CNNs

 Maksim Zhdanov 

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Jiayi Shen ·  Xiantong Zhen  · Qi (Cheems) Wang  · Marcel Worring  

The Memory-Perturbation Equation: Understanding Model’s Sensitivity to Data

Peter Nickl ·  Lu Xu · Dharmesh Tailor  · Thomas Möllenhoff  · Mohammad Emtiyaz Khan 

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers
Phillip Lippe ·  Bastiaan S. Veeling · Paris Perdikaris  · Richard E. Turner  · Johannes Brandstetter  
Rotating Features for Object Discovery

Sindy Löwe ·  Phillip Lippe  · Francesco Locatello  · Max Welling

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity 
Metod Jazbec ·  James Urquhart Allingham  · Dan Zhang · Eric Nalisnick  
Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games 
H. Hadiji ·  S. Sachs · T. van Erven  · W. M. Koolen    
First- and Second-Order Bounds for Adversarial Linear Contextual Bandits
J. Olkhovskaya ·  J. Mayo  · T. van Erven  · G. Neu· C. Wei
Geometric Algebra Transformers
Johann Brehmer ·  Pim de Haan · Sönke Behrends  · Taco Cohen   
Adaptive Selective Sampling for Online Prediction with Experts
R. M. Castro ·  F. Hellström  · T. van Erven<
Latent Field Discovery in Interacting Dynamical Systems with Neural Fields
Miltiadis Kofinas ·  Erik J Bekkers · Naveen Shankar Nagaraja  · Efstratios Gavves   
Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning
Fan Feng ·  Sara Magliacane  
Clifford Group Equivariant Neural Networks

David Ruhe ·  Johannes Brandstetter  ·  Patrick Forré  


Adapting Neural Link Predictors for Data-Efficient Complex Query Answering
Erik Arakelyan ·  Pasquale Minervini · Daniel Daza  · Michael Cochez  · Isabelle Augenstein  
Star-Shaped Denoising Diffusion Probabilistic Models

Andrey Okhotin ·  Dmitry Molchanov · Vladimir Arkhipkin  · Grigory Bartosh · Viktor Ohanesian ·  Aibek Alanov · Dmitry Vetrov


Modulated Neural ODEs

Ilze Amanda Auzina  ·  Cagatay Yildiz · Sara Magliacane · Matthias Bethges · Efstratios Gavves

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter
Ajay Jaiswal  ·  Shiwei Liu · Tianlong Chen · Zhangyang Wang 
TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

Preetha Vijayan ·  Prashant Shivaram Bhat · Bahram Zonooz  · Elahe Arani  


Dynamic Sparsity Is Channel-Level Sparsity Learner

Lu Yin ·  Gen Li · Meng Fang  · Li Shen · Tianjin Huang · Zhangyang Wang, Vlado Menkovski · Xiaolong Ma · Mykola Pechenizkiy · Shiwei Liu


Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

Hoang Pham ·  Anh Ta · Shiwei Liu · Dung D. Le · Long Tran-Thanh

Don’t just prune by magnitude! Your mask topology is a secret weapon

Duc Hoang ·  Souvik Kundu ·  Shiwei Liu · Zhangyang Wang 

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics
Koen Minartz · Yoeri Poels  · Simon Koop  · Vlado Menkovski   
Kernelized Reinforcement Learning with Order Optimal Regret Bounds

Sattar Vakili · Julia Olkhovskaya 


Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

Sarah Rastegar · Hazel Doughty · Cees G. M. Snoek 

Workshop papers
Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers

Pim De Haan ·  Taco Cohen  · Johann Brehmer   

Causal Representation Learning Workshop of the NeurIPS Conference 2023

ProtoHG: Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks

Shuai Wang ·  Jiayi Shen · Athanasios Efthymiou  · Stevan Rudinac   Monika Kackovic  · Nachoem Wijnberg  · Marcel Worring

New Frontiers in Graph Learning Workshop of the NeurIPS Conference 2023

 A Sparsity Principle for Partially Observable Causal Representation Learning

Danru Xu ·  Dingling Yao · Sebastien Lachapelle · Perouz Taslakian · Julius von Kügelgen · Francesco Locatello · Sara Magliacane

Causal Representation Learning Workshop of the NeurIPS Conference 2023

 Multi-View Causal Representation Learning with Partial Observability

Dingling Yao ·  Danru Xu · Sebastien Lachapelle · Sara Magliacane · Perouz Taslakian · Georg Martius · Julius von Kügelgen · Francesco Locatello

Causal Representation Learning Workshop of the NeurIPS Conference 2023

[Re] RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models

Paula Antequera ·  Egoitz Gonzalez · Marta Grasa  · Martijn van Raaphorst

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

LightGCN: Evaluated and Enhanced

Milena Kapralova ·  Luca Pantea · Andrei Blahovici

New in ML affinity Workshop of the NeurIPS Conference 2023

[Re] FairCal: Fairness Calibration for Face Verification

Marga Don ·  Satchit Chatterji  · Milena Kapralova ·  Ryan Amaudruz

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

On the Reproducibility of CartoonX

Elias Dubbeldam ·   Aniek Eijpe · Jona Ruthardt  · Robin Sasse  

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency

Azhar Syaikh ·  Sahar Yousefi 

Advanced Neural Network Training Workshop of the NeurIPS Conference 2023

Beyond Top-Class Agreement: Using Divergences to Forecast Performance under Distribution Shift

Mona Schirmer · Dan Zhang · Eric Nalisnick    

Distribution Shifts Workshop of the NeurIPS 2023

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Network

Taraneh Younesian ·  Thiviyan Thanapalasingam · Emile van Krieken  · Daniel Daza  ·  Peter Bloem

Distribution Shifts Workshop of the NeurIPS 2023

Hierarchical Causal Representation Learning

Angelos Nalmpantis ·  Phillip Lippe · Sara Magliacane 

Causal Representation Learning Workshop of the NeurIPS 2023

Reproducibility study of “Quantifying societal bias amplification in image captioning”

Farrukh Baratov · Goksenin Yuksel · Darie Petcu · Jan Bakker

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023