Scholar

Cheng-Yen (Wesley) Hsieh

Google Scholar ID: xUFnq1oAAAAJ

Carnegie Mellon University

Multimodal Generative AIProtein ModelingComputer VisionSelf-Supervised Learning

Citations & Impact

All-time

Citations

H-index

i10-index

Publications

Co-authors

list available

Contact

Publications

6 items

Browse publications on Google Scholar (top-right) ↗

Resume (English only)

Academic Achievements

Paper 'Elucidating the Design Space of Multimodal Protein Language Models' accepted as a Spotlight at ICML 2025 (Top 2.6% of submissions); launched the official page of DPLM series; involved in TAO-Amodal project, which addresses tracking any object amodally.

Research Experience

Currently a research scientist at ByteDance Seed, previously a Machine Learning Engineer Intern at Waymo, and a master's student at CMU RI in computer vision.

Education

Advised by Prof. Deva Ramanan during his master's in computer vision at Carnegie Mellon University; received B.S. from National Taiwan University, worked with Prof. Yu-Chiang Frank Wang and Prof. An-Yeu (Andy) Wu.

Background

Research interests include machine learning and computer vision, with a current focus on advancing AI for scientific discovery through the development of large-scale multi-modal diffusion language models. Earlier work explored self-supervised learning, amodal object tracking, federated learning, and vision-language models.

Miscellany