Jonah Casebeer

Research Scientist

San Francisco

Jonah is a research scientist and member of the Audio Research Group at Adobe Research in San Francisco. He is broadly interested in machine learning for signal processing and especially enjoys applications in audio.

He earned a Ph.D. in computer science from the University of Illinois Urbana-Champaign in the fall of 2023. Please visit his personal website for more information and publications.

Publications

REGEN: Learning Compact Video Embedding with (Re-)Generative Decoder

Zhang, Yitian., Mai, Long., Mahapatra, Aniruddha., Bourgin, David., Hong, Yicong., Casebeer, Jonah., Liu, Feng., Fu, Yun. (Oct. 19, 2025)

ICCV 2025

Learning to Upsample and Upmix Audio in the Latent Domain

Bralios, Dimitrios., Smaragdis, Paris., Casebeer, Jonah. (Oct. 13, 2025)

IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA 2025)

Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders

Bralios, Dimitrios., Casebeer, Jonah., Smaragdis, Paris. (Aug. 31, 2025)

Best Paper

IEEE International Workshop on Machine Learning for Signal Processing (MLSP 2025)

Presto! Distilling Steps and Layers for Accelerating Music Generation

Novack, Zachary., Zhu, Ge., Casebeer, Jonah., McAuley, Julian., Berg-Kirkpatrick, Taylor., Bryan, Nicholas. (Apr. 24, 2025)

Spotlight

International Conference on Learning Representations (ICLR 2025)

Meta-AF: Meta-Learning for Adaptive Filters

Casebeer, Jonah., Bryan, Nicholas., Smaragdis, Paris. (Nov. 23, 2022)

IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP 2022)