Kun Su
Scholar

Kun Su

Google Scholar ID: y52GkywAAAAJ
Google Research
Multimodal LearningAudio/Music GenerationRecommendation system
Citations & Impact
All-time
Citations
809
 
H-index
13
 
i10-index
14
 
Publications
20
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Publications: 'How Does it Sound? Generation of Rhythmic Soundtracks for Human Movement Videos' (NeurIPS 2021), 'Audeo: Audio Generation for a Silent Performance Video' (NeurIPS 2020), 'Predict & Cluster: Unsupervised Skeleton Based Action Recognition' (CVPR 2020), 'Clustering and Recognition of Spatiotemporal Features through Interpretable Embedding of Sequence to Sequence Recurrent Neural Networks', 'Cooperative parameter identification of advection-diffusion processes using a mobile sensor network'.
Research Experience
  • Software Engineer at Google Research starting March 2024; Internship at Google Research in Fall 2022; Internship at MIT-IBM Watson AI lab in Summer 2022.
Education
  • PhD in Electrical & Computer Engineering, 2019-2024, University of Washington-Seattle; M.S. in Electrical & Computer Engineering, 2017-2019, University of Washington-Seattle; B.S. in Electrical Engineering, 2013-2017, Rensselaer Polytechnic Institute (RPI). During undergrad, did research with Prof. Wencen Wu on control and robotics.
Background
  • Research interests: deep learning, computer vision, and audio/music signal processing. Ph.D. student at the University of Washington NeuroAI Lab, advised by Prof. Eli Shlizerman.
Miscellany
  • Interests include multi-modal learning, audio/music generation, and computer vision.