Daniel Rubenstein

The paper introduces β-Stability, a graph-based framework for semi-automated curation of animal identities from images, achieving high accuracy with limited expert review.

RAPID re-identifies patterned animal images in real-time on edge devices with high accuracy and efficiency using SIFT descriptors and optimized vector similarity search.

This study investigates convergent wing pattern evolution in Heliconius butterflies using GWAS, comparative genomics, and machine learning, identifying both known and novel genetic loci associated with color patterns.

The paper quantifies mimetic similarity in Heliconius butterflies using deep learning and visual system models, revealing geographic organization and perceptual asymmetry in mimicry.

The paper models predator group dynamics and prey population interactions, finding that flexible group sizes lead to smaller stable groups and unexpected resource partitioning between prey types.