Utkarsh Saxena
Papers
1
Total Citations
41
H-Index
1
About
Utkarsh Saxena is a leading researcher at the forefront of hardware-software co-design for artificial intelligence, with a core focus on compute-in-memory (CIM) architectures and emerging technologies for deep learning acceleration. His work addresses the critical challenge of the "memory wall" in modern AI systems, where data movement between memory and processing units creates severe energy and latency bottlenecks. Saxena’s most-cited paper, "Compute-in-Memory Technologies and Architectures for Deep Learning Workloads" (2022, 41 citations), provides a comprehensive survey that has become a foundational reference for researchers and engineers designing next-generation AI hardware. The paper systematically analyzes how CIM can enable more efficient execution of deep learning workloads in applications ranging from computer vision to robotics. By bridging the gap between device-level innovations and system-level performance, Saxena’s contributions are helping to drive the virtuous cycle of algorithms, data, and computing capacity that fuels modern AI. His work is particularly influential for students and researchers seeking to understand how to build more energy-efficient, high-performance AI accelerators for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1Compute-in-Memory Technologies and Architectures for Deep Learning Workloads41 citations · 2022