collaborators

5 papers

cs.CL2026

Two-dimensional early exit optimisation of LLM inference

Jan Hůla, David Adamczyk, Tomáš Filip +2

We introduce a two-dimensional (2D) early exit strategy that coordinates layer-wise and sentence-wise exiting for classification tasks in large language models. By processing input…

cs.LG2026

Geometric Reasoning in the Embedding Space

Jan Hůla, David Mojžíšek, Jiří Janeček +2

In this contribution, we demonstrate that Graph Neural Networks and Transformers can learn to reason about geometric constraints. We train them to predict spatial position of point…

cs.LG2025

Minimizing the Weighted Number of Tardy Jobs: Data-Driven Heuristic for Single-Machine Scheduling

Nikolai Antonov, Prěmysl Šůcha, Mikoláš Janota +1

Existing research on single-machine scheduling is largely focused on exact algorithms, which perform well on typical instances but can significantly deteriorate on certain regions…

cs.CL2025

BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism

Martin Fajcik, Martin Docekal, Jan Dolezal +15

We present BenCzechMark (BCM), the first comprehensive Czech language benchmark designed for large language models, offering diverse tasks, multiple task formats, and multiple eval…

cs.LG2025

Neural Approaches to SAT Solving: Design Choices and Interpretability

David Mojžíšek, Jan Hůla, Ziwei Li +2

In this contribution, we provide a comprehensive evaluation of graph neural networks applied to Boolean satisfiability problems, accompanied by an intuitive explanation of the mech…