Newest papers

CellTrack-Bench: Microscopic Cell Tracking Benchmark for Vision-Language Models

Ilan F. S. Theodoro, Jordão Bragantini, Löıc A. Royer · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31566 · cited by 0 works (OpenAlex) · open-access PDF

German

Große Sprachmodelle haben eine hervorragende Leistung bei Text-First-Tasks wie Codierung, Mathematik und Schreiben gezeigt. Die jüngsten Bemühungen verschieben die Ausbildung von Modellen, um wissenschaftliche Probleme einzubeziehen, die oft in hochspezialisierten Domänen außerhalb des Textes leben, wie Proteinstruktur und biologische Bilder. In diesen Szenarien wird jedoch ihre allgemeine Zweckgenauigkeit im Vergleich zu spezialisierten Algorithmen in Frage gestellt. Eines dieser Domänen ist das Zelltracking, das räumlich-zeitliche Bewusstsein für Zelldynamik erfordert. Um dies zu beurteilen, haben wir einen neuen Benchmark, CellTrack-Bench, erstellt, der die Leistung von Vision-Language-Modellen (VLMs) im Vergleich zu spezialis

Machine translation (Meta M2M100); the English original follows.

Abstract

Large language models have shown outstanding performance on text-first tasks such as coding, math, and writing. Recent efforts are shifting models' training to include scientific problems that often live in highly specialized domains beyond text, such as protein structure and biological images. However, in these scenarios, their general-purpose accuracy compared with specialized algorithms remains in question. One such domain is cell tracking, which requires spatiotemporal awareness of cell dynamics. To evaluate this, we created a new benchmark, CellTrack-Bench, which assesses Vision-Language Models' (VLMs) cell-tracking-related performance against specialized trackers. The full benchmark draws from 15 standard cell-tracking datasets across four imaging modalities and comprises 1,537 problems corresponding to 9,041 cell-linking decisions. We selected a hard subset requiring greater reasoning effort by identifying failures shared across distinct algorithmic trackers. With this proposed dataset, we: (i) evaluated different environment harnesses for VLMs; (ii) benchmarked 9 frontier closed-source models and 13 open-weight models; and (iii) provided a detailed analysis of their failure modes. Code, the stored model outputs, and a pipeline that regenerates the benchmark from the source datasets are available at https://github.com/royerlab/celltrack-bench.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Benchmark (surveying), Pipeline (software), Computer science, Domain (mathematical analysis), Artificial intelligence, Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange