97 citations
- Trinity College DublinIE3 papers
- University College DublinIE3 papers
- University of ViennaAT3 papers
- Bulgarian Academy of SciencesBG2 papers
- Carnegie Mellon UniversityUS2 papers
- Fraunhofer Institute for Telecommunications, Heinrich Hertz InstituteDE2 papers
- Intelligent Machines (Sweden)SE2 papers
- Technische Universität BerlinDE2 papers
- University College CorkIE2 papers
- Aalto UniversityFI1 paper
- Aarhus UniversityDK1 paper
- Aberystwyth UniversityGB1 paper
Showing 2025 · cs.LGShow all
2 papers · 2 filters
cs.LG2025
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker +5
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to b…
cs.LG2025
FADE: Why Bad Descriptions Happen to Good Features
Bruno Puri, Aakriti Jain, Elena Golimblevskaia +4
Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While t…