3 papers
cs.LG2026
A Structural Theory of Position Bias in Transformers
Hanna Herasimchyk, Robin Labryga, Tomislav Prusina +1
Transformer models systematically favor certain token positions, yet the architectural origins of this position bias remain poorly understood. This bias is closely connected to the…
cs.LG2025
Joint Design of Protein Surface and Structure Using a Diffusion Bridge Model
Guanlue Li, Xufeng Zhao, Fang Wu +1
Protein-protein interactions (PPIs) are governed by surface complementarity and hydrophobic interactions at protein interfaces. However, designing diverse and physically realistic…
math.OC2025
Information Preserving Line Search via Bayesian Optimization
Robin Labryga, Tomislav Prusina, Sören Laue
Line search is a fundamental part of iterative optimization methods for unconstrained and bound-constrained optimization problems to determine suitable step lengths that provide su…