Zeyang Zheng

Zeyang Zheng

Auto-generated profile, based on publicly available information

Zeyang Zheng

University of Virginia, Charlottesville, USA

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 November 2025
Verified
Conference Paper
Open access
ZZZeyang Zheng
Zeyang Zheng
SNSeyed Hamidreza Nabaei
Seyed Hamidreza Nabaei
Somayeh AsadiSomayeh Asadi
Somayeh Asadi
BCBrad Campbell
Brad Campbell
AHArsalan Heydarian
Arsalan Heydarian

3 August 2026 in Automation in Construction
Verified
Journal Article
Closed access
ANAmir Farzin Nikkhah
Amir Farzin Nikkhah
KKKyung Y Kim
Kyung Y Kim
ZZZeyang Zheng
Zeyang Zheng
VLVenkataraman Lakshmi
Venkataraman Lakshmi
AHArsalan Heydarian
Arsalan Heydarian

7 November 2026 in ACM Transactions on Sensor Networks
Verified
Journal Article
Open access
ZZZeyang Zheng
Zeyang Zheng
SNSeyed Hamidreza Nabaei
Seyed Hamidreza Nabaei
ANAmir Farzin Nikkhah
Amir Farzin Nikkhah
HLHunter Frederick Lutz
Hunter Frederick Lutz
BCBrad Campbell
Brad Campbell
AHArsalan Heydarian
Arsalan Heydarian
Home inspection evaluates the visible components of a residential building and reports their deficiencies, safety concerns, and recommended actions. Vision–language models (VLMs) can describe what a photograph shows, but inspection findings also require regulatory knowledge, system-level assessment, and familiarity with inspection practice. We present MASHI, a multi-agent vision–language system that answers home inspection questions across the ten systems of the ASHI Standard of Practice. A planner agent routes each question to an ASHI system and assigns tasks to a perception agent and a system agent. The perception agent reports visual evidence from the question’s photograph. The system agent applies the agent skill of the selected ASHI system to the question, its task, and this evidence. When needed, it retrieves text and images through multimodal retrieval-augmented generation (RAG) from a knowledge base of 45 building code editions and 18 inspection reports. For evaluation, a semi-automated pipeline with human verification turns 84 other inspection reports into 32,554 question–answer pairs. Prometheus-2 and Phi-4 rate the answers on a five-level rubric. MASHI reaches a mean judge score of 4.083, higher than those of all other compared systems, including its single-agent variant. Every difference is statistically significant.

11 November 2025
Verified
Conference Paper
Open access
SNSeyed Hamidreza Nabaei
Seyed Hamidreza Nabaei
ZZZeyang Zheng
Zeyang Zheng
BCBrad Campbell
Brad Campbell
AHArsalan Heydarian
Arsalan Heydarian