1.8k citations · 3.3k across the 25 of their papers we have counts for
31 papers
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
Björn Engdahl, Adrian Kosowski, Jan Chorowski +6
We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs presented at inference time continuously update the model's recurre…
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain
Adrian Kosowski, Przemysław Uznański, Jan Chorowski +2
The relationship between computing systems and the brain has served as motivation for pioneering theoreticians since John von Neumann and Alan Turing. Uniform, scale-free biologica…
Pathway: a fast and flexible unified stream data processing framework for analytical and Machine Learning applications
Michal Bartoszkiewicz, Jan Chorowski, Adrian Kosowski +8
We present Pathway, a new unified data processing framework that can run workloads on both bounded and unbounded data streams. The framework was created with the original motivatio…
Efficient Transformers with Dynamic Token Pooling
Piotr Nawrot, Jan Chorowski, Adrian Łańcucki +1
Transformers achieve unrivalled performance in modelling language, but remain inefficient in terms of memory and time complexity. A possible remedy is to reduce the sequence length…
Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
Santiago Cuervo, Adrian Łańcucki, Ricard Marxer +2
The success of deep learning comes from its ability to capture the hierarchical structure of data by learning high-level representations defined in terms of low-level ones. In this…
Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
Santiago Cuervo, Maciej Grabias, Jan Chorowski +4
We investigate the performance on phoneme categorization and phoneme and word segmentation of several self-supervised learning (SSL) methods based on Contrastive Predictive Coding…