NeurIPS Fest 2024
The 2024 NeurIPS conference and workshops will be held in Vancouver, Canada from 10th to 15th December. Prior to the major event, the NeurIPS Fest will be organised by the ELLIS unit Amsterdam. This year, we invite papers presenters from different universities across the Netherlands. Therefore, we organize the event closely with the other two ELLIS units located in the country; ELLIS unit Delft and ELLIS unit Nijmegen.
As done in the past two years, we will celebrate the achievements of the Machine Learning ecosystem members with a keynote speaker, poster session, and networking. Grab this fantastic opportunity to connect with like-minded individuals and explore the latest research in Machine Learning in the Netherlands!
We are looking forward to seeing you at the event!
Event details:
Date: 28 November 2024
Time: 16:00 – 19:30
Location: LAB42, Amsterdam Science Park
Programme of activities:
16:00-17:00 Keynote Presentation by Christian A. Naesseth, Machine Learning Assistant Professor at University of Amsterdam, ELLIS Member (venue: L3.33 & L3.35)
17:00-19:30 Poster session with bites and drinks (venue: Ground floor)
Keynote Talk
Christian A. Naesseth
Title: ‘Diffusions, flows, and other stories’
Abstract: Generative models have taken the world by storm. Using generative modeling, a.k.a. generative AI, we can construct probabilistic approximations to any data-generating process. In the context of text, large language models place distributions over the next token, for images it is often a distribution over pixel color values, whereas for molecules it can be a combination of atom types, positions, and various chemical features. This talk will explore some of the dominant paradigms, applications, and recent developments in generative modeling.
Bio:
Christian A. Naesseth is an Assistant Professor of Machine Learning at the University of Amsterdam, a member of the Amsterdam Machine Learning Lab, the lab manager of the UvA-Bosch Delta Lab 2, and an ELLIS member.
His research interests span statistical inference, uncertainty quantification, reasoning, and machine learning, as well as their application to the sciences. He is currently working on generative modelling(diffusions, flows, AI4Science), approximate inference (variational and Monte Carlo methods), uncertainty quantification and hypothesis testing (E-values, conformal prediction). Previously, he was a postdoctoral research scientist with David Blei at the Data Science Institute, Columbia University. He completed his PhD in Electrical Engineering at Linköping University, advised by Fredrik Lindsten and Thomas Schön.
At the 2024 NeurIPS Conference, his lab and collaborators will present 5 accepted papers
Registration is required for logistics purposes
Are you based in the Netherlands and do you have a paper accepted at the 2024 NeurIPS Conference?
Please sign up by filling out the form here: https://forms.office.com/e/g9Vc8jGreE
Presented papers
Equivariant Neural Diffusion for Molecule Generation
François Cornet · Grigory Bartosh · Mikkel Schmidt · Christian A. NaessethVariational Flow Matching for Graph Generation
Floor Eijkelboom · Grigory Bartosh Christian A. Naesseth ·Max Welling ·Jan-Willem van de MeentSpace-Time Continuous PDE Forecasting using Equivariant Neural Fields
David M. Knigge · David R. Wessels · Riccardo Valperga · Samuele Papa · Jan-Jakob Sonke · Efstratios Gavves · Erik J. Bekkers
PART: Self-supervised Pre-Training with Continuous Relative Transformations
Melika AyoughiWhen Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
Leon Lang · Davis Foote · Stuart Russell · Anca Dragan · Erik Jenner · Scott Emmons
VISA: Variational Inference with Sequential Sample-Average Approximations
Heiko Zimmermann · Christian A. Naesseth · Jan-Willem van de MeentScalable Kernel Inverse Optimization
Youyuan Long · Tolga Ok · Pedro Zattoni Scroccaro · Peyman Mohajerin Esfahani
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
Ruihong Yin · Vladimir Yugay · Yue Li · Sezer Karaoglu · Theo Gevers[Re] On the Reproducibility of Post-Hoc Concept Bottleneck Models
Nesta Midavaine · Gregory Hok Tjoan Go · Diego Canez · Ioana Simion · Satchit Chatterji
Rethinking Knowledge Transfer in Learning Using Privileged Information
Danil Provodin · Bram van den Akker · Christina Katsimerou · Maurits Kaptein · Mykola PechenizkiyTVBench: Redesigning Video-Language Evaluation
Daniel Cores · Michael Dorkenwald· Manuel Mucientes · Cees G. M. Snoek · Yuki M. AsanoSIGMA: Sinkhorn-Guided Masked Video Modeling Main
Mohammadreza Salehi · Michael Dorkenwald · Fida Mohammad Thoker · Efstratios Gavves · Cees G. M. Snoek · Yuki M. Asano