arXiv subjects

Pawel Pawlowski

Publications and source records attributed to Pawel Pawlowski.

5 recordsLinked to original sources

arXiv2026

Medvedev Logic is Not Decidable. It is π01 -complete. Who Would Have Guessed?

This project began as an attempt to prove that Medvedev logic is decidable with the help of generative AI systems. The author (as well as the generative AI systems, or at least they claim to be since I have asked them) was surprised by its eventual conclusion. We prove that Medvedev logic ML, the intermediate logic of finite problems, is Pi-01-complete under computable many-one reductions. Consequently, ML is not recursively enumerable, a fortiori undecidable, and admits no recursively enumerable sound and complete proof calculus. The proof connects the periodic domino problem with intuitionistic formulas through a shared intermediate structure that we call a Wang-Medvedev pair. Such a pair consists of a finite partially ordered set of roles together with demands. Demands define the interaction between roles. A realization labels nonempty subsets of a finite set with these roles, respecting the order and satisfying the demands. We associate a pair with each finite Wang system and show that it has a realization iff the system tiles a finite torus. We then construct an intuitionistic formula that fails on some finite Medvedev frame iff the same pair is realizable. Realizability thus provides the link between periodic tilings and the countermodels.

cs.LO↗

arXiv2025

T-BAT semantics and its logics

\textbf{T-BAT} logic is a formal system designed to express the notion of informal provability. This type of provability is closely related to mathematical practice and is quite often contrasted with formal provability, understood as a formal derivation in an appropriate formal system. \textbf{T-BAT} is a non-deterministic four-valued logic. The logical values in \textbf{T-BAT} semantics convey not only the information whether a given formula is true but also about its provability status. The primary aim of our paper is to study the proposed four-valued non-deterministic semantics. We look into the intricacies of the interactions between various weakenings and strengthenings of the semantics with axioms that they induce. We prove the completeness of all the logics that are definable in this semantics by transforming truth values into specific expressions formulated within the object language of the semantics. Additionally, we utilize Kripke semantics to examine these axioms from a modal perspective by providing a frame condition that they induce. The secondary aim of this paper is to provide an intuitive axiomatization of \textbf{T-BAT} logic.

cs.LO↗

arXiv2025

TinyClick: Single-Turn Agent for Empowering GUI Automation

We present an UI agent for user interface (UI) interaction tasks, using Vision-Language Model Florence-2-Base. The agent's primary task is identifying the screen coordinates of the UI element corresponding to the user's command. It demonstrates very strong performance on Screenspot and OmniAct annotations, while maintaining a very small size of 0.27B parameters and minimal latency. Moreover, training needs small compute budget of 56 GPU-hours (worth about 40 USD). Relevant improvement comes from vision-specific multi-task training and MLLM-based data augmentation. We hope that decreased needs for expensive compute resources and manually annotated data will allow to facilitate more inclusive and sustainable research of UI agents.

cs.HC↗

arXiv2025

Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models

This paper explores ideas and provides a potential roadmap for the development and evaluation of physics-specific large-scale AI models, which we call Large Physics Models (LPMs). These models, based on foundation models such as Large Language Models (LLMs) - trained on broad data - are tailored to address the demands of physics research. LPMs can function independently or as part of an integrated framework. This framework can incorporate specialized tools, including symbolic reasoning modules for mathematical manipulations, frameworks to analyse specific experimental and simulated data, and mechanisms for synthesizing theories and scientific literature. We begin by examining whether the physics community should actively develop and refine dedicated models, rather than relying solely on commercial LLMs. We then outline how LPMs can be realized through interdisciplinary collaboration among experts in physics, computer science, and philosophy of science. To integrate these models effectively, we identify three key pillars: Development, Evaluation, and Philosophical Reflection. Development focuses on constructing models capable of processing physics texts, mathematical formulations, and diverse physical data. Evaluation assesses accuracy and reliability by testing and benchmarking. Finally, Philosophical Reflection encompasses the analysis of broader implications of LLMs in physics, including their potential to generate new scientific understanding and what novel collaboration dynamics might arise in research. Inspired by the organizational structure of experimental collaborations in particle physics, we propose a similarly interdisciplinary and collaborative approach to building and refining Large Physics Models. This roadmap provides specific objectives, defines pathways to achieve them, and identifies challenges that must be addressed to realise physics-specific large scale AI models.

physics.data-an↗

arXiv2024

Large Language Models for Expansion of Spoken Language Understanding Systems to New Languages

Spoken Language Understanding (SLU) models are a core component of voice assistants (VA), such as Alexa, Bixby, and Google Assistant. In this paper, we introduce a pipeline designed to extend SLU systems to new languages, utilizing Large Language Models (LLMs) that we fine-tune for machine translation of slot-annotated SLU training data. Our approach improved on the MultiATIS++ benchmark, a primary multi-language SLU dataset, in the cloud scenario using an mBERT model. Specifically, we saw an improvement in the Overall Accuracy metric: from 53% to 62.18%, compared to the existing state-of-the-art method, Fine and Coarse-grained Multi-Task Learning Framework (FC-MTLF). In the on-device scenario (tiny and not pretrained SLU), our method improved the Overall Accuracy from 5.31% to 22.06% over the baseline Global-Local Contrastive Learning Framework (GL-CLeF) method. Contrary to both FC-MTLF and GL-CLeF, our LLM-based machine translation does not require changes in the production architecture of SLU. Additionally, our pipeline is slot-type independent: it does not require any slot definitions or examples.

cs.CL↗