activity
20232026
most citedFine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

33 citations · 34 across the 5 of their papers we have counts for

collaborators

5 papers

astro-ph.CO2026

Global 21cm Measurement Calibration Methodology

Martin Bucher, Christian J. Kirkham, Eloy de Lera Acedo +2

21cm global signal observations present a unique set of calibration challenges owing to the absolute character of the required measurement. Since differential measurements on the s…

cs.CL2024★ 33 cited

Fine-Tuned 'Small' LLMs (Still) Significantly Outperform Zero-Shot Generative AI Models in Text Classification

Martin Juan José Bucher, Marco Martini

Generative AI offers a simple, prompt-based alternative to fine-tuning smaller BERT-style LLMs for text classification tasks. This promises to eliminate the need for manually label…

astro-ph.IM2024

Representation of a Noisy Transmission Line

Martin Bucher, Daniel Molnar

We analyse a lossy transmission line and the Johnson-Nyquist noise generated therein. A representation as a noisy two-port with a voltage and a current noise sources on one end of…

astro-ph.IM2024

Representations of Noisy -Ports

Martin Bucher, Daniel Molnar

Much has been written about the representation of noisy linear 2-ports. Here we present a theory of noisy -ports. We show how in the general case there are equiva…

cs.DS2023★ 1 cited

Quantitative Comparison of Nearest Neighbor Search Algorithms

Hanitriniala Malalatiana Rakotondrasoa, Martin Bucher, Ilya Sinayskiy

We compare the performance of three nearest neighbor search algorithms: the Orchard, ball tree, and VP-tree algorithms. These algorithms are commonly used for nearest-neighbor sear…