activity
20242026
collaborators
Showing cs.LGShow all

22 papers · 1 filter

cs.LG2026

LieSolver: PDE-Constrained Learning for IBVPs via Lie Symmetries

René P. Klausen, Ivan Timofeev, Jonas Naujoks +4

Initial-boundary value problems (IBVPs) provide the essential framework for modelling a wide range of phenomena in physics and engineering. We introduce a novel method for efficien…

cs.LG2026

The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network

Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek

Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents. But does algorithmic structu…

cs.LG2026

Predicting Future Behaviors in Reasoning Models Enables Better Steering

Evgenii Kortukov, Piotr Komorowski, Florian Klein +5

Deployed large reasoning models (LRMs) often behave unexpectedly. Test-time steering controls LRM outputs by intervening on their hidden representations, but it can degrade output…

cs.LG2026

PINNfluence: Interpreting PINNs through Influence Functions

Aleksander Krasowski, Jonas R. Naujoks, Moritz Weckbecker +5

Physics-informed neural networks (PINNs) have emerged as a powerful deep learning approach for solving partial differential equations (PDEs) in the physical sciences, yet their beh…

cs.LG2026

Playing the network backward: A Game Theoretic Attribution Framework

Jakob Paul Zimmermann, Jim Berend, Georg Loho +2

Attribution methods explain which input features drive a model's prediction, making them central to model debugging and mechanistic interpretability. Yet backward attribution metho…

cs.LG2026

Attribution-Guided Pruning for Insight and Control: Circuit Discovery and Targeted Correction in Small-scale LLMs

Sayed Mohammad Vakilzadeh Hatefi, Maximilian Dreyer, Reduan Achtibat +5

Large Language Models (LLMs) are widely deployed in real-world applications, yet their internal mechanisms remain difficult to interpret and control, limiting our ability to diagno…