Jiamian Hugo HU

Artificial intelligence is transforming research by providing more efficient tools and enabling new research paradigms. My research explores how AI methods can be integrated into biology to help scientists tackle some of the most interesting and challenging scientific questions.

I began by developing an image analysis system to automate the identification, counting, and measurement of ostracods, small crustaceans found in nearly all aquatic environments. We scaled this system to measure more than 1,000,000 ostracods, creating the world’s largest database of ostracod measurements and enabling scientists to investigate the causes of phenotypic change at scale.

I have also explored systematic ways to use large language models (LLMs) in biological research, extracting information from a corpus of 36,229 ostracod-related papers. Using these data, I built a similarity-based taxonomic system that helps researchers find specimens in the published literature that resemble their own. This work provides a proof of concept for using LLMs to build large-scale, evidence-based taxonomic systems. I also trained a series of specialist ostracod LLMs using the data.

My broader goal is to investigate global changes in ostracod diversity across space and time. These data allow us to explore fundamental questions: What is the current state of ostracod biodiversity? How has ostracod diversity changed over the past 400 million years?

I am also deeply interested in how AI actually works: what happens inside its “mind”? If you are interested in how AI could help your research, welcome to contact me. My other interests include philosophy, hiking, and diving.

Email: hujiamian1234567[at]gmail[dot]com

Ostracod Expert LLMs: https://huggingface.co/Jiamian/qwen3.5-27B-ostracod_focused-sft

My blog: https://h-jamieu.github.io/my_blog/