← Search

James Balhoff

2 accepted papers

2025

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

NeurIPS 2025spotlight

Foundation models trained at scale exhibit remarkable emergent behaviors, learning new capabilities beyond their initial training objectives. We find such emergent behaviors in biological vision models via large-scale contrastive vision-language training. To achieve this, we first curate TreeOfLife-…

Cited by 0SourcecodeScholar
2024

VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images

NeurIPS 2024poster

Images are increasingly becoming the currency for documenting biodiversity on the planet, providing novel opportunities for accelerating scientific discoveries in the field of organismal biology, especially with the advent of large vision-language models (VLMs). We ask if pre-trained VLMs can aid sc…