My name is Wei-Yao Wang. I am a research scientist in the Creative AI Lab at Sony, working on interactive multimodal models for content creation, spanning omni‑modal LLMs/embedders, video generation/editing, and agentic understanding. I received my Ph.D. and BS degrees from National Yang Ming Chiao Tung University and National Chiao Tung University in Taiwan respectively, advised by Prof. Wen-Chih Peng. During my academic journey, I served as a visiting researcher at the ScAi lab advised by Prof. Wei Wang at the University of California, Los Angeles. I was a research intern at Document AI in Microsoft in Seattle and Microsoft AI R&D Center in Taipei advised by Paul Hsu, working on low-resource field extractions from multi-modal documents with LLMs.

My research intersts include Interactive Omnimodal Models; Multimodal LLMs; LLM Agents; Multimodal Representation Learning; Video Generation & Understanding; and Creative AI; which has been published more than 40+ papers in international journals and major peer-reviewed conference proceedings (e.g., ICLR, NeurPS, ICML, CVPR, KDD, AAAI, ACL, EMNLP), including multiple best paper awards. I serve on the program committees of international conferences including ICLR, ICCV, AAAI, ACL ARR, KDD, IJCAI, CIKM, and PAKDD and workshop organizers (GenProCC@NeurIPS-25, IT4PSS@IJCAI23-24, SocialNLP@NAACL-22&TheWebConf-22).

I am also open to research collaboration. Please drop me an email if you are interested in.

Research Experience & Education

Publications

Click a paper to expand details. ^♠ denotes papers I mentored.

Selected Mentored Journals and Conferences Workshops

Academic Services

Honors and Awards

Competition Awards