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

French

Les grands modèles linguistiques ont montré des performances exceptionnelles sur les tâches de premier texte telles que le codage, les mathématiques et l'écriture. Les efforts récents changent la formation des modèles pour inclure des problèmes scientifiques qui vivent souvent dans des domaines hautement spécialisés au-delà du texte, tels que la structure des protéines et les images biologiques. Cependant, dans ces scénarios, leur précision générale par rapport aux algorithmes spécialisés reste en question. L'un de ces domaines est le suivi cellulaire, qui nécessite une prise de conscience spatiotemporelle de la dynamique cellulaire. Pour évaluer cela, nous avons créé un nouveau critère de référence, CellTrack-Bench, qui évalue les performances liées

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