1 citations · 1 across the 4 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.LG2026
Better Policies, Worse Verifier Audits
Daniel Cieślak, Jacek Łubiński
Verifier stacks increasingly sit inside post-training and test-time compute loops. We study a specific control loop: a component verifier is evaluated on fresh policy outputs again…
physics.comp-ph2026
Input-schema identifiability limits in physics-informed surrogates for mechanics-governed flow
Daniel Cieslak, Andrzej Czyzewski
Physics-informed and data-driven surrogates are increasingly used to approximate mechanics-governed flow fields, but the target quantities assigned to such models are not always id…
cs.LG2026
Decision-Aware Evaluation of Physics-Informed Surrogates
Daniel Cieślak, Andrzej Czyżewski
Physics-informed machine learning is often assessed by curve error, although engineering use depends on downstream decisions: ranking candidates, avoiding infeasible designs and li…