Xuhui Zhan · Applied Scientist

Curiosity,
built into
systems.

I turn research questions into working AI. My work connects multimodal learning, recommendation systems, and the infrastructure that brings them to life.

A connected practice

Follow a point. Explore the work.

01 / 06Treverse Recsys

Currently building at Treverse LLC ↗

Research ↔ production Nashville, TN

02 / How I work

Research and production,
in one loop.

A useful model is only part of the story. I follow the question through evaluation, deployment, and what the system teaches us next.

Method / 05

Each stage opens the project that best demonstrates it.

01 / 05

Frame the question.

Ancient Mortars structures roughly 10 million particle images for comparison.

Open project
02 / 05

Fit the representation.

Inverse-LLaVA maps text into visual space inside the language model.

Open project
03 / 05

Make the comparison legible.

Negotiation transcript coding reports a cost drop from more than $5,000 to $3.

Open project
04 / 05

Publish a reviewable release.

FORGE defines six contracts across distinct ML runtimes.

Open project
05 / 05

Return field evidence.

Treverse joins controlled exposure with reproducible learning and serving.

Open project
An illustrated portrait of Xuhui at graduation

Beyond the models

A curious mind.
A human behind the work.

My interests take me from language models to archaeological materials. Away from the work, there’s usually coffee and Mino, my coding companion.

Meet Mino