output
20092026
most citedOn the use of Self-supervised Pre-trained Acoustic and Linguistic Features for Continuous Speech Emotion Recognition

55 citations

10 papers

cs.LG2026

Flawed in Nature, Perfect through Evolution

J. M. Diederik Kruijssen

The performance of artificial intelligence (AI) and machine learning (ML) models degrades when the problem they were trained on drifts. This is a near-universal feature of real-wor…

cs.LG2026

Stroke Lesions as a Rosetta Stone for Language Model Interpretability

Julius Fridriksson, Roger D. Newman-Norlund, Saeed Ahmadi +10

Large language models (LLMs) have achieved remarkable capabilities, yet methods to verify which model components are truly necessary for language function remain limited. Current i…

cs.LG2025★ 4 cited

Efficient PINNs via Multi-Head Unimodular Regularization of the Solutions Space

Pedro Tarancón-Álvarez, Pablo Tejerina-Pérez, Raul Jimenez +1

Non-linear differential equations are a fundamental tool to describe different phenomena in nature. However, we still lack a well-established method to tackle stiff differential eq…

astro-ph.IM2023★ 8 cited

Parameterizing pressure-temperature profiles of exoplanet atmospheres with neural networks

Timothy D. Gebhard, Daniel Angerhausen, Björn S. Konrad +3

Atmospheric retrievals (AR) of exoplanets typically rely on a combination of a Bayesian inference technique and a forward simulator to estimate atmospheric properties from an obser…

astro-ph.GA2023★ 8 cited

Simulation of CHOH ice UV photolysis under laboratory conditions

W. R. M. Rocha, P. Woitke, S. Pilling +5

Methanol is the most complex molecule securely identified in interstellar ices and is a key chemical species for understanding chemical complexity in astrophysical environments. Im…

astro-ph.GA2022★ 7 cited

Spectropolarimetry and spectral decomposition of high-accreting Narrow Line Seyfert 1 galaxies

Marzena Śniegowska, Swayamtrupta Panda, Bożena Czerny +7

Narrow Line Seyfert 1 (NLSy1) galaxies have been shown to have high Eddington ratios and relatively small black hole masses. The measurement of the black hole masses is based on th…