Newest papers

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

Ilan Theodoro, Jordão Bragantini, Loïc A. Royer · 2026 · arXiv

DOI: 10.48550/arXiv.2610.31566 · open-access PDF

Indonesian

Model bahasa besar telah menunjukkan kinerja yang luar biasa pada tugas-tugas teks pertama seperti pengkodean, matematika, dan penulisan. Upaya baru-baru ini mengubah pelatihan model untuk mencakup masalah ilmiah yang sering hidup di domain yang sangat khusus di luar teks, seperti struktur protein dan gambar biologis. Namun, dalam skenario ini, akurasi tujuan umum mereka dibandingkan dengan algoritma khusus tetap dipertanyakan. Salah satu domain tersebut adalah pelacakan sel, yang membutuhkan kesadaran spatiotemporal tentang dinamika sel. Untuk mengevaluasi ini, kami menciptakan benchmark baru, CellTrack-Bench, yang menilai Vision-Language

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

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

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