- Passed the PhD qualifying exam (August 12, 2025)
- Paper 'SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval' presented at ICME 2025
- Paper 'CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models' accepted by ICML 2025
- Paper 'SD-NAE: Generating Natural Adversarial Examples with Stable Diffusion' presented at ICLR 2024 in the Tiny Papers track
- Paper 'Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and KiSing-v2' uploaded to arXiv
- Paper 'EEG-Based Speech Envelope Decoding: Structured State Space and U-Net Model Integration' accepted by National Conference on Man-Machine Speech Communication 2023
- Paper 'BiSinger: Bilingual Singing Voice Synthesis' accepted by IEEE ASRU 2023
- Poster 'RTVis: Research Trend Visualization Toolkit' presented at IEEE VIS 2023
- Released SD-NAE method
- Released RTVis tool
- Published a paper on in-situ AFM tracking of nanoparticles in ACM Macro Letters
Research Experience
- Research Intern at Adobe Research (Summer 2025)
- ECE PhD student at the CEI lab (Fall 2024 - present)
Education
- Degree: Bachelor's in Data Science
- School: Duke University and Duke Kunshan University
- Advisors: Prof. Ming Li and Prof. Kai Zhang
- Graduation: May 2024
- Honors: Summa cum laude, signature work distinction, valedictorian
Background
- Research Interests: Multimodal large language models, with a focus on audio and vision understanding and generation
- Field: Electrical and Computer Engineering
- Brief: ECE PhD student at Duke University, advised by Prof. Yiran Chen and Prof. Hai “Helen” Li.