activity
20162025
most citedAccelerating scientific discovery with Co-Scientist

87 citations · 87 across the 3 of their papers we have counts for

collaborators

5 papers

cs.AI2025★ 87 cited

Accelerating scientific discovery with Co-Scientist

Juraj Gottweis, Wei-Hung Weng, Alexander Daryin +48

Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce C…

cs.LG2020

Replacing Human Audio with Synthetic Audio for On-device Unspoken Punctuation Prediction

Daria Soboleva, Ondrej Skopek, Márius Šajgalík +8

We present a novel multi-modal unspoken punctuation prediction system for the English language which combines acoustic and text features. We demonstrate for the first time, that by…

cs.LG2019

Decoupling Hierarchical Recurrent Neural Networks With Locally Computable Losses

Asier Mujika, Felix Weissenberger, Angelika Steger

Learning long-term dependencies is a key long-standing challenge of recurrent neural networks (RNNs). Hierarchical recurrent neural networks (HRNNs) have been considered a promisin…

cs.NE2018

The linear hidden subset problem for the (1+1) EA with scheduled and adaptive mutation rates

Hafsteinn Einarsson, Marcelo Matheus Gauy, Johannes Lengler +4

We study unbiased evolutionary algorithms on linear functions with an unknown number of bits with non-zero weight. Static algorithms achieve an optimal runtime of $O(n…

math.CO2016

A tight Erdős-Pósa function for long cycles

Frank Mousset, Andreas Noever, Nemanja Škorić +1

A classic result of Erdős and Pósa says that any graph contains either vertex-disjoint cycles or can be made acyclic by deleting at most vertices. Here we general…