25 citations · 37 across the 10 of their papers we have counts for
12 papers
Knowledge transfer between simple discrete worlds
Silvère Gangloff, Jan Hula
Adapting to a new world and reasoning correctly about which outcomes are possible under rules one has not met before is a basic capacity underlying general intelligence. We study i…
Proving at Scale for Universal Algebra
João Araújo, Jan Hůla, Mikoláš Janota +2
We introduce SemiBase, a project that computes and formally certifies finite identity bases for small semigroups. Deciding finite basability is undecidable for finite algebras and…
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…
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…
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…
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…
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…
Understanding GNNs for Boolean Satisfiability through Approximation Algorithms
Jan Hůla, David Mojžíšek, Mikoláš Janota
The paper deals with the interpretability of Graph Neural Networks in the context of Boolean Satisfiability. The goal is to demystify the internal workings of these models and prov…
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
Mikail Khona, Maya Okawa, Jan Hula +5
Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Desp…
Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
Petr Hurtik, Vojtech Molek, Jan Hula +3
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two…
Identifying collaborators in large codebases
Waren Long, Vadim Markovtsev, Hugo Mougard +2
The way developers collaborate inside and particularly across teams often escapes management's attention, despite a formal organization with designated teams being defined. Observa…
Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling
Alex Wang, Jan Hula, Patrick Xia +13
Natural language understanding has recently seen a surge of progress with the use of sentence encoders like ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2019) which are pre…