Skip to content Search
28.05.2024
Our researchers returned from ICLR red carpets in Vienna, having met colleagues from CVC Barcelona, Stanford, Riken Institute (Japan), MIT, Oxford, Cambridge and much more. Although the community was fairly cautious in anticipating the arrival of AGI, Yoshua Bengio, one of fathers of AI explained that researchers should double our efforts on AI safety, as AGI can happen any day from now.

At ICLR, there were four papers co-authored by IDEAS NCBR researchers:

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan, Tomasz Trzciński, Bartosz Zieliński, Bartłomiej Twardowski (all IDEAS NCBR)

https://arxiv.org/abs/2401.10191

Magnushammer: A Transformer-Based Approach to Premise Selection

Maciej Mikuła, Szymon Antoniak (IDEAS NCBR), Szymon Tworkowski, Bartosz Piotrowski (IDEAS NCBR), Albert Jiang, Jin Peng Zhou, Christian Szegedy, Łukasz Kuciński (IDEAS NCBR), Piotr Miłoś (IDEAS NCBR), Yuhuai Wu

https://arxiv.org/abs/2303.04488

MoE-Mamba: Efficient Selective State Space Models with Mixture of Experts

Maciej Pióro, Kamil Ciebiera, Krystian Król, Jan Ludziejewski, Michał Krutul, Jakub Krajewski (all IDEAS NCBR), Szymon Antoniak, Piotr Miłoś (IDEAS NCBR), Marek Cygan, Sebastian Jaszczur (IDEAS NCBR)

https://arxiv.org/abs/2401.04081

Discovering modular solutions that generalize compositionally

Simon Schug, Seijin Kobayashi, Yassir Akram, Maciej Wołczyk (IDEAS NCBR), Alexandra Proca, Johannes von Oswald, Razvan Pascanu, João Sacramento, Angelika Steger

https://arxiv.org/abs/2312.15001

Featured news

20.06.2024
Krzysztof Walas joins Adra Board of Directors
06.06.2024
HALG 2024 is over
28.05.2024
Back from ICLR 2024