activity
20192023
most citedEliminating Sandwich Attacks with the Help of Game Theory

51 citations · 90 across the 12 of their papers we have counts for

collaborators

18 papers

cs.CL20232 cited

Exponentially Faster Language Modelling

Peter Belcak, Roger Wattenhofer

Language models only really need to use an exponential fraction of their neurons for individual inferences. As proof, we present UltraFastBERT, a BERT variant that uses 0.3% of its…

cs.LG2023

SURF: A Generalization Benchmark for GNNs Predicting Fluid Dynamics

Stefan Künzli, Florian Grötschla, Joël Mathys +1

Simulating fluid dynamics is crucial for the design and development process, ranging from simple valves to complex turbomachinery. Accurately solving the underlying physical equati…

cs.CL2022

Beyond Prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations

Yu Fei, Ping Nie, Zhao Meng +2

Recent work has demonstrated that pre-trained language models (PLMs) are zero-shot learners. However, most existing zero-shot methods involve heavy human engineering or complicated…

cs.LG2022

A Neural Model for Regular Grammar Induction

Peter Belcák, David Hofer, Roger Wattenhofer

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computa…

cs.LG2022

Periodic Extrapolative Generalisation in Neural Networks

Peter Belcák, Roger Wattenhofer

The learning of the simplest possible computational pattern -- periodicity -- is an open problem in the research of strong generalisation in neural networks. We formalise the probl…

cs.LG20221 cited

FACT: Learning Governing Abstractions Behind Integer Sequences

Peter Belcák, Ard Kastrati, Flavio Schenker +1

Integer sequences are of central importance to the modeling of concepts admitting complete finitary descriptions. We introduce a novel view on the learning of such concepts and lay…