ABOUT ME: I am a second-year PhD student in the Department of Computer Science at Johns Hopkins University. I am a member of the Lions Vision Research & Rehab Center, Wilmer Eye Institute and Artificial Intelligence for Engineering and Medicine Lab. I am advised by Dr. Yingzi Xiong and Prof. Rama Chellappa. My research interest lies in multi-modality fusion, 2D and 3D segmentation, as well as human-computer interaction, especially in clinical applications.
- 2026.05.19. Oral Presentation at VSS -- "Where is my cereal? Impacts of target saliency and background complexity on visual search at home"
- 2026.05.03. Oral Presentation at ARVO -- "What's in Front of Me?" Comparing Hand Gestures for Disambiguating Targets While Using Smart Glasses.
- 2026.05.03. Our work 'Real-world Scene Text with Low Vision' is accepted to ARVO 2026.
- 2026. Our work 'A Very Big Video Reasoning Suite' is accepted to ICML 2026.
- 👁 Low Vision Behavior Simulation
- Text Accessibility: Simulating low-vision reading with OCR and contrast sensitivity functions to assess text readability.
- Navigation: Simulating low vision’s personalized vision and behavior during navigation in familiar and unfamiliar environments.
- Object Labeling: Real-life object boundary tracing using wearable smart glasses.
- Font Accessibility: Evaluating font designs for low-vision readers via behavioral and automated methods.
- 🧠 Generative Model
- Core Knowledge: Benchmarking VLMs on developmental psychology concepts and exposing shortcut learning.
- Theory of Mind: Evaluating intention understanding, perspective-taking, and gaze direction inference.
- Video Reasoning: Building million-scale video reasoning benchmarks with verifiable evaluation.
- 💉 Medical AR
HCI, VLM TOM, Ophthalmology