Ph.D. Candidate, NTU EECS · Taipei, Taiwan
I am a Ph.D. student at National Taiwan University (NTU), advised by Jyh-Shing Roger Jang and Hung-yi Lee.
Prior to this, I earned my M.S. and B.S. in Computer Science from
NTU (2023) and
Taiwan Tech (2020).
My research focuses on large language models, audio language models, audio generation, and deepfakes, with more than 10 first/co-first papers published in top-tier venues such as TASLP, TIST, COLM, ICASSP, INTERSPEECH, ASRU, and SLT.
I have been fortunate to receive several research honors, highlighted by:
IEEE Signal Processing Society Scholarship.Recently, I have been working on training and benchmarking models for audio understanding and generation, building on my earlier work across three main threads: leading research on retrieval and agentic LLMs (MetaBench-Harness, CodaRAG, GDP-RAG); spearheading work on audio deepfakes (SingGraph, CodecFake+, SASTNet); and also contributing to community-wide audio-language model and benchmark efforts (Dynamic-SUPERB Phase-2, Codec-SUPERB, DeSTA 2.5-Audio).
I am actively seeking a 2027 research internship. If you would like to exchange ideas or discuss research, feel free to reach out to me at d12942018 [at] ntu.edu.tw or find me on LinkedIn, Scholar, GitHub, and 𝕏.
See all publications by topic →