Zehao Wen portrait

I study CS at Johns Hopkins as a freshman, currently researching Embodied Intelligence.

I also have hands-on experience in full-stack development with SwiftUI (iOS) and Flutter (Progressive Web App), as well as in deploying AI models into real-world applications.

Besides, I enjoy photography, collecting vinyls, and reading sci-fis. I love "chill walking": wandering without a goal but enjoying the movement, the talks, and the thoughts along.

Publications

AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes

Rao Fu*, Zehao Wen*, Zichen Liu*, and Srinath Sridhar

ECCV 2024

INTP-Video-LLMs: Toward Longer-sequence LMMs in a Training-free Manner

Yuzhang Shang*, Bingxin Xu*, Weitai Kang, Mu Cai, Yuheng Li, Zehao Wen, Zhen Dong, Kurt Keutzer, Jae Lee Yong*, and Yan Yan*

ArXiv 2024

CONF-CDS 2023

Highlighted Projects

KangEr: an LLM+RAG health Q&A application made for rural doctors in China

A chatbot-style PWA that provides accurate medical knowledge and basic diagnostic suggestions. Used by 80+ rural doctors in Fujian and Henan provinces; 800+ users.

Acealth: DL-based complete health checkup with only a 45-second facial video

A PWA that analyzes a 45-second facial video to extract photoplethysmography signals, from which 15 vital signs (e.g. blood pressure) and the risk of 14 diseases (e.g. heart failure) are predicted, using deep learning models on a secure cloud server.

TwoStep: an all-in-one airport and travel companion application

An iOS app featuring 8 utilities for travel: airport maps, security queue waiting time info, airport info, translator, transportation recommendation, immigration policy info, cultural tips, and a LLM chatbot. Features derived from 100+ street market interviews at UMich.