Sy-Tuyen Ho | PhD Student @ University of Maryland College Park

About Me

I am a PhD student at the University of Maryland College Park working with Prof. Furong Huang. Previously, I earned a Master's degree from the Singapore University of Technology and Design advised by Prof. Ngai-Man Cheung; and a Bachelor from the University of Information Technology - Vietnam National University Ho Chi Minh City working with Dr. Tiep Nguyen and Prof. Tam Nguyen.

I’m deeply interested in building trustworthy and reliable AI for multimodal and agentic systems.

Personal Interests

Ping Pong Cooking Hiking

Beyond research, I'm always up for a friendly ping pong match, experimenting with new recipes in the kitchen or exploring scenic trails on a hike!

News

May, 2026 SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones? is now on arXiv.

March, 2026 Two papers accepted to CVPR 2026: On data privacy of VLMs (Main Track) and Faithful Multimodal Evaluation Framework for Model Inversion (Findings Track)

Sep, 2025 Started my PhD in CS at University of Maryland, College Park

Previous news

Sep, 2024 One paper accepted to NeurIPS 2024. Embedding dimension is key for ViT Out-of-Distribution generalization

Jul, 2024 One paper accepted to ECCV 2024. Skip connection reinforces adversary

Mar, 2024 One paper accepted to CVPR 2024. Transfer learning prevents data leakage

Jan, 2024 Started my Master of Engineering at SUTD

Education

University of Maryland, College Park PhD in Computer Science

Singapore University of Technology and Design M.Eng (Research)

University of Information Technology, Vietnam National University, HCMC B.Sc in Computer Science (Honour)

Experience

University of Maryland College Park Teaching Assistant

CMSC848N: Generative AI Agents

Temasek Lab @ SUTD Research Assistant

Viettel Group Intern

Academic Services

Conference Reviewer (2025-now) NeurIPS, ICLR, ICML, ACM MM, AAAI, CVPR

Journal Reviewer (2024-now) TMM

Selected Publications (First/Joint-First/Leading Author)

SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?

Sy-Tuyen Ho, Minghui Liu, Huy Nghiem, Furong Huang

Under Review

Paper

Dataset

Code Project

Memory Makes The Poison: Over Memorization Drives Visual Poisoning in LVLMs

Sy-Tuyen Ho, Y.R.A. Epa, K. Liu, X. Jiang, A. Kot, F. Huang, N.M. Cheung

Under Review

Paper

Code Project

Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment

Sy-Tuyen Ho, K.J. Hao, N.B. Nguyen, A. Binder, N.M. Cheung

CVPR 2026 Findings

Paper

Dataset

Code Project

Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization

Sy-Tuyen Ho*, T.V. Vo*, S. Ebrahimkhani*, N.M. Cheung

NeurIPS 2024

Paper

Dataset

Code Project

On the Vulnerability of Skip Connections to Model Inversion Attacks

K.J. Hao*, Sy-Tuyen Ho*, N.B. Nguyen, N.M. Cheung

ECCV 2024

Paper

Code Project

Model Inversion Robustness: Can Transfer Learning Help?

Sy-Tuyen Ho, K.J. Hao, K. Chandrasegaran, N.B. Nguyen, N.M. Cheung

CVPR 2024

Paper

Code Project

Agentic Critical Training

Weize Liu, Minghui Liu, Sy-Tuyen Ho, Souradip Chakraborty, Xiyao Wang, Furong Huang

Under Review

Paper

Bias in the Tails: How Name-conditioned Evaluative Framing in Resume Summaries Destabilizes LLM-based Hiring

Huy Nghiem, Phuong-Anh Nguyen-Le, Sy-Tuyen Ho, Hal Daume III

Under Review

Paper

Model Inversion Attacks on Vision-Language Models: Do They Leak What They Learn?

N.B. Nguyen, Sy-Tuyen Ho, K.J. Hao, N.M. Cheung

CVPR 2026

Paper

Code Project