NeurIPS Fest 2023

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

December 7, 2023

17:00-20:00

Lab42, Amsterdam Science Park

Come and deep dive into the state-of-the-art machine learning research that will be showcased at the NeurIPS Conference in New Orleans!

Event programme

17:00-18:00

Keynote Presentation

Prof. Juergen Gall (University of Bonn)
Venue: L1.01

18:00-20:00

Poster Session

with bites & drinks
Venue: ground floor

Prof. Dr. Juergen Gall

Professor and Head of Computer Vision Group at the University of Bonn

About the 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

Implicit Convolutional Kernels for Steerable CNNs

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games

Latent Field Discovery in Interacting Dynamical Systems with Neural Fields

Star-Shaped Denoising Diffusion Probabilistic Models

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

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

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

Learning to Learn Prototypical Networks by Task-Guided Diffusion

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

Geometric Algebra Transformers

Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

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

Kernelized Reinforcement Learning with Order Optimal Regret Bounds

Learning Unseen Modality Interaction

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

Rotating Features for Object Discovery

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

Adaptive Selective Sampling for Online Prediction with Experts

Clifford Group Equivariant Neural Networks

Modulated Neural ODEs

Dynamic Sparsity Is Channel-Level Sparsity Learner

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics

Workshop papers

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

Causal Representation Learning Workshop of the NeurIPS Conference 2023

Multi-View Causal Representation Learning with Partial Observability

Causal Representation Learning Workshop of the NeurIPS Conference 2023

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

Advanced Neural Network Training Workshop of the NeurIPS Conference 2023

Hierarchical Causal Representation Learning

Causal Representation Learning Workshop of the NeurIPS 2023

ProtoHG: Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks

New Frontiers in Graph Learning Workshop of the NeurIPS Conference 2023

LightGCN: Evaluated and Enhanced

New in ML affinity Workshop of the NeurIPS Conference 2023

[Re] FairCal: Fairness Calibration for Face Verification

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

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

Distribution Shifts Workshop of the NeurIPS 2023

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

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

A Sparsity Principle for Partially Observable Causal Representation Learning

Causal Representation Learning Workshop of the NeurIPS Conference 2023

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

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

On the Reproducibility of CartoonX

Machine Learning Reproducibility Challenge of the NeurIPS Conference 2023

GRAPES: Learning to Sample Graphs for Scalable Graph Neural Network

Distribution Shifts Workshop of the NeurIPS 2023

The NeurIPS Fest 2023 is ELLIS unit Amsterdam’s annual NeurIPS-preview party spotlighting Amsterdam’s finest and latest research in machine learning.