Skip to content Search
‘For a PhD Student who wants to put his research “out there”, the best thing about NeurIPS is that, during this week, most of the experts in your field are literally at your fingertips. You can walk up to anyone, ask them questions about their research and let them know what you’re doing. We should really encourage young researchers to attend such events,’ says Marcin Przewięźlikowski, PhD student at Jagiellonian University and IDEAS NCBR.

NeurIPS2023 is over. ‘It’s challenging to envision a better place to be as a PhD student,’ says Daniel Marczak, studying at Warsaw University of Technology and IDEAS NCBR, who presented the paper ‘Revisiting Supervision for Continual Representation Learning’. ‘Witnessing how individuals are pushing the frontiers of science is truly inspiring.’

NeurIPS 2023 (only the IDEAS NCBR affiliation was noted):

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Jan Dubiński (IDEAS NCBR), Stanisław Pawlak, Franziska Boenisch, Tomasz Trzciński (IDEAS NCBR), Adam Dziedzic         

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Wojciech Masarczyk, Mateusz Ostaszewski, Ehsan Imani, Razvan Pascanu, Piotr Miłoś (IDEAS NCBR),          Tomasz Trzciński (IDEAS NCBR)       

Focused Transformer: Contrastive Training for Context Scaling

Szymon Tworkowski (IDEAS NCBR), Konrad Staniszewski (IDEAS NCBR), Mikołaj Pacek (IDEAS NCBR),     Yuhuai Wu, Henryk Michalewski, Piotr Miłoś  (IDEAS NCBR)      

Trust Your ∇: Gradient-based Intervention Targeting for Causal Discovery

Mateusz Olko (IDEAS NCBR), Michał Zając, Aleksandra Nowak, Nino Scherrer, Yashas Annadani, Stefan Bauer, Łukasz Kuciński (IDEAS NCBR), Piotr Miłoś (IDEAS NCBR)

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

Aleksandra Nowak (w IDEAS NCBR podczas prowadzenia badań), Bram Grooten, Decebal Constantin Mocanu, Jacek Tabor 

NeurIPS 2023 workshops:

Revisiting Supervision for Continual Representation Learning

Daniel Marczak, Sebastian Cygert, Tomasz Trzciński, Bartłomiej Twardowski (wszyscy z IDEAS NCBR)  

Augmentation-aware Self-supervised Learning with Guided Projector

Marcin Przewięźlikowski (IDEAS NCBR), Mateusz Pyla (IDEAS NCBR), Bartosz Zieliński (IDEAS NCBR), Bartłomiej Twardowski (IDEAS NCBR), Jacek Tabor, Marek Śmieja

Featured news

5 papers at ECCV 2024
Breakthroughs require freedom and patience
Krzysztof Walas joins Adra Board of Directors