Trong-Tung Nguyen

CS PhD student @ Johns Hopkins University

Data Science and AI Institute

tnguy303 [AT] jh [DOT] edu

Biography

Hi, I'm a Computer Science PhD student at Johns Hopkins University, where I have the privilege of working with Prof. Anand Bhattad.

Prior to JHU, I was an AI Research Resident at Qualcomm AI Research, under the mentorship of Principal Scientist Anh Tran and Prof. Cuong Pham. My passion for research began as an undergraduate at VNU-HCMUS, under the mentorship of Prof. Tran Minh Triet.

My past research focused on efficient generative models for visual generation: image editing, inpainting, and personalization. My current research explores physics-informed video generation models, which enable physics realism in generated videos, and 3D physics simulation, which enables dynamic physics on static 3D representations.

News

[May 26] Honored to receive the ✨ Outstanding Reviewer badge (top 5% of reviewers) at CVPR26.
[Feb 26] 🥂 InverFill and SwiftPie got accepted to CVPR26 (main, finding). TLDR: InverFill enables fast image inpainting via inversion on few-step diffusion backbones, and SwiftPie contextualizes your subject image with new prompt at lightning speed.
[Jan 26] Career Update: Joined the Department of Computer Science at Johns Hopkins University as a Ph.D. student, working with Prof. Anand Bhattad.
[Oct 25] Honored to receive the 🥇 Best Resident Award 2025 at Qualcomm AI Research, in recognition of outstanding contributions to both research and applied engineering.
[Feb 25] 🥂 SwiftEdit got accepted to CVPR 2025. TLDR: SwiftEdit achieves lightning-fast speed in text-guided image editing.
[Aug 23] Career Update: Joined Qualcomm AI Research as AI Research Resident.

Education

Johns Hopkins University
Ph.D. in Computer Science, Jan. 2026 - Present
Advisor: Prof. Anand Bhattad

Ho Chi Minh City University of Science, VNU-HCM
B.S. in Advanced Program in Computer Science, 2022
Summa Cum Laude. GPA: 3.92/4.0
Advisor: Prof. Minh-Triet Tran

Experience

Qualcomm AI Research
AI Research Resident, Aug. 2023 - Dec. 2025
Mentors: Principal Scientist Anh Tran & Prof. Cuong Pham

VinUni-Illinois Smart Health Center
Research Assistant and Teaching Assistant, 2022
Advisors: Prof. Minh Do & Prof. Wray Buntine

Singapore Management University
Visiting AI Researcher, 2023
Advisor: Prof. Guansong Pang

Publications & Selected Preprints

	Preprint 2026 PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams Trong-Tung Nguyen, Anand Bhattad Preprint, 2026 TLDR: Physics 3D simulation with PowerFoam representation. Paper Project Page
	Preprint 2026 FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation Trong-Tung Nguyen, Jiahan Zhang, Anand Bhattad Preprint, 2026 TLDR: Teaching video generation models to stretch and tear objects. Paper Project Page
	CVPR 2026 InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting Duc Vu, Kien Nguyen, Trong-Tung Nguyen, Ngan Nguyen, Phong Nguyen, Khoi Nguyen, Cuong Pham, Anh Tran * Equal contribution Computer Vision and Pattern Recognition 2026 (CVPR 2026), Main TLDR: Enables fast image inpainting via inversion on few-step diffusion backbones. Paper Project Page
	CVPR 2026 SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusion Huy Duong, Trong-Tung Nguyen*, Cuong Pham, Anh Tran, Khoi Nguyen, Minh Hoai Equal contribution Computer Vision and Pattern Recognition 2026 (CVPR 2026), Findings TLDR: Contextualizes your subject image with a new prompt at lightning speed. Paper
	CVPR 2025 SwiftEdit: Lightning Fast Text-guided Image Editing via One-step Diffusion Trong-Tung Nguyen, Quang Nguyen, Khoi Nguyen, Anh Tran, Cuong Pham Computer Vision and Pattern Recognition 2025 (CVPR 2025), Main TLDR: Edits your image with text at lightning speed. Paper Project Page
	Preprint 2024 FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing Trong-Tung Nguyen, Duc-Anh Nguyen, Anh Tran, Cuong Pham Preprint, 2024 TLDR: Make controllable object edits with prompts and spatial conditions. Paper Project Page
	ACCV 2022 Multi-stream Fusion for Class Incremental Learning in Pill Image Classification Trong-Tung Nguyen, Hieu H. Pham, Phi Le Nguyen, Thanh Hung Nguyen, Minh Do Asian Conference on Computer Vision 2022 (ACCV 2022) Paper Code