Ph.D. Researcher · Incoming UNC Charlotte, August 2026

Haohan Yuan

I study how structural priors can make LLM, multimodal, and agentic systems more reliable, explainable, and controllable.

I am a Computer Science Ph.D. student at the University of Hawaii at Manoa, advised by Prof. Haopeng Zhang. In August 2026, I will transfer to the University of North Carolina at Charlotte with my advisor, with my Ph.D. coursework and qualifying exam transferred. My research spans LLM reasoning, long-context understanding, model attribution, multimodal systems, and embodied agents.

Academic path: B.Sc. in Mathematics and Applied Mathematics, Hefei University of Technology (2018–2022) · M.Eng. in Computer Science, Nanyang Technological University (2022–2024), advised by Prof. Siu Cheung Hui · Ph.D. study in Computer Science, University of Hawaii at Manoa (August 2024–July 2026) · Incoming Ph.D. student, UNC Charlotte (August 2026).

Seeking research internship and visiting student opportunities.
Haohan Yuan
Reliable & Explainable AI LLMs · Multimodal · Agentic AI
5Selected publications
4First-author papers
2Ongoing directions
4Major AI/NLP venues
What I am building now

🤖 Research Highlights

Extending structured reasoning and reliability from language models to multimodal and embodied systems.

StrucVLA structured task state overview
Multimodal AIVLAEmbodied AI

StrucVLA

Structural Priors for Explainable Vision-Language-Action Policies

Exposing high-level VLA understanding as explicit scene, task, interaction, and progress states that can be supervised, diagnosed, and controlled.

Ongoing research
SumFingerprint attribution and fragility overview
Reliable LLMsAttributionRobustness

SumFingerprint

Reliability and Fragility of LLM Summary Fingerprints

Investigating whether model-specific fingerprints in generated summaries remain trustworthy under rewriting and targeted transformation attacks.

Ongoing research
Research journey

From structured language reasoning to reliable AI systems

Biomedical IE Summarization & Evaluation Reliable LLMs Multimodal & Embodied Agents

My published work studies structured reasoning, faithfulness, and robustness in summarization. I am now carrying those ideas into agentic AI and vision-language-action policies.

Structured reasoning methods for summarization View research figure
Selected work

📚 Publications

All publications
ACL2026

Understanding LLM Reasoning for Abstractive Summarization

Haohan Yuan, Haopeng Zhang

Studies how explicit reasoning strategies affect summarization quality and factual faithfulness.

ICML2026

Position: Generative Engine Optimization Creates Underexamined Risks

Yizhu Wen, Nan Zhang, Haohan Yuan, Xun Chen, Haopeng Zhang, Hanqing Guo

Identifies governance risks involving concentrated influence, disclosure, and evaluation blind spots.

Paper
EACL2026

StrucSum: Graph-Structured Reasoning for Long Document Extractive Summarization with LLMs

Haohan Yuan, Sukhwa Hong, Haopeng Zhang

Proposes graph-structured sentence-level reasoning over long documents.

NAACL2025

DomainSum: A Hierarchical Benchmark for Fine-Grained Domain Shift in Abstractive Text Summarization

Haohan Yuan, Haopeng Zhang

Benchmarks summarization robustness and generalization under fine-grained domain shifts.

DASFAA2025

A Structure-aware Generative Model for Biomedical Event Extraction

Haohan Yuan, Siu Cheung Hui, Haopeng Zhang

Introduces structure-aware generation for complex biomedical event extraction.

Latest updates

✨ Recent News

ICML 2026

Our position paper on the risks and governance of Generative Engine Optimization was accepted.

Upcoming transfer to UNC Charlotte

I will transfer to the University of North Carolina at Charlotte with my advisor in August 2026, with my Ph.D. coursework and qualifying exam transferred.

AI @ HIDSI Fellowship

I received an offer for the 2026 fellowship from the Hawaii Data Science Institute.

ACL 2026 (Findings)

Our work on LLM reasoning for abstractive summarization was accepted.

EACL 2026 (Findings)

Our StrucSum paper on graph-structured long-document reasoning was accepted.

AI @ HIDSI Fellowship

I received the 2025 fellowship from the Hawaii Data Science Institute.

Research feature

Our work was featured in University of Hawaii News.

NAACL 2025 (Findings)

Our DomainSum paper on fine-grained domain shift in summarization was accepted.

Ph.D. journey begins

I joined the University of Hawaii at Manoa as a Computer Science Ph.D. student.

Let us connect

Interested in reliable LLMs or structured multimodal systems?

I am always happy to discuss research ideas, collaborations, and internship opportunities.

haohany@hawaii.edu