
Texas ECE graduate student Dan Jacobellis and assistant professor Neeraja Yadwadkar have received the Capocelli Prize for Best Paper at the Data Compression Conference (DCC) 2025. DCC is an international forum for current work on data compression and related applications. The Capocelli Prize is awarded annually by the DCC program committee for an outstanding student-authored and presented DCC paper, in memory of Renato M. Capocelli (May 3, 1940 – April 8, 1992) a friend and colleague who served on the DCC program committee during its initial two years.
The paper, “Learned Compression for Compressed Learning," addresses unlocking new possibilities for AI on power and bandwidth constrained devices such as wearables and satellites.
Paper Summary:
Sensors embedded in modern devices—from smartphones to medical equipment and autonomous vehicles—generate vast, high-resolution data streams that power emerging Machine Learning (ML) models. Although today’s ML models can process fine-grained data with super-human speed and accuracy, the data must be highly compressed for storage and transmission—something existing methods like JPEG and MPEG struggle to achieve without quality loss. To bridge this gap, we developed a new compression system that delivers unprecedented compression ratios while preserving quality, using only a fraction of the computational cost of leading neural network methods—unlocking new possibilities for AI on power- and bandwidth-constrained devices like wearables and satellites.
Dan Jacobellis is a Ph.D student in Texas ECE, where he also received a BSEE in 2017 and MSEE in 2021. In 2023, he joined the UT-SysML lab as a graduate research assistant. His interests include signal processing, data compression, and representation learning.
Neeraja Yadwadkar is an assistant professor and is a Fellow of the Advanced Micro Devices (AMD) Chair in Computer Engineering in the Chandra Family Department of Electrical and Computer Engineering at The University of Texas at Austin. She is a Cloud Computing Systems researcher, with a strong background in Machine Learning (ML). Most of her research straddles the boundaries of Systems and ML. Advances in systems, ML, and hardware architectures are about to launch a new era in which we can use the entire cloud as a computer.