arXiv subjects

Pavlin G. Poličar

Publications and source records attributed to Pavlin G. Poličar.

7 recordsLinked to original sources

arXiv2026

Is manual software optimization a thing of the past?

Scientific software is increasingly required to process larger datasets while maintaining acceptable execution times. Software optimization traditionally requires substantial expertise in programming, algorithms, and numerical methods. Recent advances in large language models (LLMs) offer the possibility of automating much of this process. We investigate whether LLM-based agents can autonomously achieve substantial performance improvements in scientific software, including mature implementations that have already been extensively optimized by human developers. We tasked an LLM-based agent with optimizing software for three computational problems: t-SNE, single-sample gene set enrichment analysis (ssGSEA), and graphlet counting. Humans defined the scope, correctness criteria, and a verification mechanism, after which the agent worked autonomously, in some cases for several hours. Code maintainers reviewed each resulting implementation and verified its correctness. The optimized implementations were faster in all tested configurations, by up to two orders of magnitude over the fastest existing tools. The improvements included low-level code optimizations, mathematical reformulations, and an entirely new algorithm for graphlet counting. Software optimization can increasingly be delegated to autonomous agents, with the human role shifting from implementing optimizations to deciding which software to optimize, defining objectives, providing verification mechanisms, and ensuring the correctness of the final software. For well-scoped, verifiable problems, we argue that manual software optimization may be a thing of the past.

cs.SE↗

arXiv2026

Generating Statistical Charts with Validation-Driven LLM Workflows

Generating diverse, readable statistical charts from tabular data remains challenging for LLMs, as many failures become apparent after rendering and are not detectable from data or code alone. Existing chart datasets also rarely provide fully aligned artifacts, such as executable code, dataset context, and question-answer pairs. We present a structured LLM-based workflow that decomposes chart generation into dataset screening, plot proposal, code synthesis, rendering, validation-driven refinement, description generation, and question-answer generation. By incorporating rendered-output validation, the workflow addresses visualization-specific failure modes such as readability and semantic mismatch. It treats chart generation as an inspectable process rather than a one-shot prompt-to-code task, retaining each chart with its code, dataset context, description, and question-answer pairs. Applied to UCI datasets, the workflow produces 1,500 charts from 74 datasets, spanning 24 chart families and paired with 30,003 question-answer pairs. We evaluate 16 multimodal LLMs (MLLMs) on these chart-question pairs. The results show that chart-syntax questions are nearly saturated, while value extraction, comparison, and reasoning remain more challenging, illustrating the workflow's utility for diagnostic studies of chart-grounded multimodal reasoning.

cs.LG↗

arXiv2026

VERA: Generating Visual Explanations of Two-Dimensional Embeddings via Region Annotation

Two-dimensional embeddings obtained from dimensionality reduction techniques such as MDS, t-SNE, or UMAP, are widely used to visualize high-dimensional data and support researchers in visually identifying clusters, outliers, and other interesting patterns in the data. However, the main challenge is not only to detect such patterns, but to explain what they represent in terms of the original, human-interpretable features of the data. Existing approaches often rely on interactive exploration or direct feature encodings, requiring substantial manual inspection that can be time-consuming and repetitive. As an alternative, we propose VERA (Visual Explanations via Region Annotation), a general-purpose method for explaining two-dimensional embeddings through automatically generated, static, region-based visual explanations. VERA identifies informative regions in the embedding space and associates them with user-provided human-interpretable features, producing concise visual annotations that summarize the structure of the embedding landscape at a glance. Rather than merely showing where feature values occur, VERA automatically filters, merges, and ranks candidate explanations, enabling users to focus on the most informative embedding structures without manual exploration. We demonstrate VERA's utility on several real-world datasets and evaluate its effectiveness in a user study comparing it with the utility of a comprehensive interactive data mining toolkit. Our results show that VERA's generated static explanations can convey the essential insights of complex embeddings and support users in typical exploratory data analysis tasks, while requiring significantly less time and user effort.

cs.LG↗

arXiv2026

Inferring Chronic Treatment Onset from ePrescription Data: A Renewal Process Approach

Longitudinal electronic health record (EHR) data are often left-censored, making diagnosis records incomplete and unreliable for determining disease onset. In contrast, outpatient prescriptions form renewal-based trajectories that provide a continuous signal of disease management. We propose a probabilistic framework to infer chronic treatment onset by modeling prescription dynamics as a renewal process and detecting transitions from sporadic to sustained therapy via change-point detection between a baseline Poisson (sporadic prescribing) regime and a regime-specific Weibull (sustained therapy) renewal model. Using a nationwide ePrescription dataset of 2.4 million individuals, we show that the approach yields more temporally plausible onset estimates than naive rule-based triggering, substantially reducing implausible early detections under strong left censoring. Detection performance varies across diseases and is strongly associated with prescription density, highlighting both the strengths and limits of treatment-based onset inference.

cs.LG↗

arXiv2025

Low-dimensional embeddings of high-dimensional data

Large collections of high-dimensional data have become nearly ubiquitous across many academic fields and application domains, ranging from biology to the humanities. Since working directly with high-dimensional data poses challenges, the demand for algorithms that create low-dimensional representations, or embeddings, for data visualization, exploration, and analysis is now greater than ever. In recent years, numerous embedding algorithms have been developed, and their usage has become widespread in research and industry. This surge of interest has resulted in a large and fragmented research field that faces technical challenges alongside fundamental debates, and it has left practitioners without clear guidance on how to effectively employ existing methods. Aiming to increase coherence and facilitate future work, in this review we provide a detailed and critical overview of recent developments, derive a list of best practices for creating and using low-dimensional embeddings, evaluate popular approaches on a variety of datasets, and discuss the remaining challenges and open problems in the field.

cs.LG↗

arXiv2025

Automated Assignment Grading with Large Language Models: Insights From a Bioinformatics Course

Providing students with individualized feedback through assignments is a cornerstone of education that supports their learning and development. Studies have shown that timely, high-quality feedback plays a critical role in improving learning outcomes. However, providing personalized feedback on a large scale in classes with large numbers of students is often impractical due to the significant time and effort required. Recent advances in natural language processing and large language models (LLMs) offer a promising solution by enabling the efficient delivery of personalized feedback. These technologies can reduce the workload of course staff while improving student satisfaction and learning outcomes. Their successful implementation, however, requires thorough evaluation and validation in real classrooms. We present the results of a practical evaluation of LLM-based graders for written assignments in the 2024/25 iteration of the Introduction to Bioinformatics course at the University of Ljubljana. Over the course of the semester, more than 100 students answered 36 text-based questions, most of which were automatically graded using LLMs. In a blind study, students received feedback from both LLMs and human teaching assistants without knowing the source, and later rated the quality of the feedback. We conducted a systematic evaluation of six commercial and open-source LLMs and compared their grading performance with human teaching assistants. Our results show that with well-designed prompts, LLMs can achieve grading accuracy and feedback quality comparable to human graders. Our results also suggest that open-source LLMs perform as well as commercial LLMs, allowing schools to implement their own grading systems while maintaining privacy.

cs.LG↗

arXiv2024

Uncovering Temporal Patterns in Visualizations of High-Dimensional Data

With the increasing availability of high-dimensional data, analysts often rely on exploratory data analysis to understand complex data sets. A key approach to exploring such data is dimensionality reduction, which embeds high-dimensional data in two dimensions to enable visual exploration. However, popular embedding techniques, such as t-SNE and UMAP, typically assume that data points are independent. When this assumption is violated, as in time-series data, the resulting visualizations may fail to reveal important temporal patterns and trends. To address this, we propose a formal extension to existing dimensionality reduction methods that incorporates two temporal loss terms that explicitly highlight temporal progression in the embedded visualizations. Through a series of experiments on both synthetic and real-world datasets, we demonstrate that our approach effectively uncovers temporal patterns and improves the interpretability of the visualizations. Furthermore, the method improves temporal coherence while preserving the fidelity of the embeddings, providing a robust tool for dynamic data analysis.

cs.LG↗