Vijay Raghunathan
Engineering · Purdue University West Lafayette
Publications
165
Citations
7,689
Est. group size
~3
Recurring co-author estimate
Active years
27
Publishing since 2000
Vijay Raghunathan works on making computing hardware and systems more energy-efficient, particularly for embedded devices, edge computing, and Internet of Things (IoT) applications. Recent work focuses on designing specialized chips called Neural Processing Units (NPUs) that efficiently run AI models like graph neural networks and other emerging network architectures on small, resource-limited devices. His research also explores approximate computing, a technique that trades a small amount of accuracy for large energy savings across sensing, computing, memory, and communication systems.
Publication output dipped in the early 2020s (including a gap in 2022) but has picked up again since 2024, with 2025 showing notably higher activity.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- MOSAIC: A Workload-Driven Simulation and Design-Space Exploration Framework for Heterogeneous NPUs
arXiv (Cornell University) · 2026
- BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference
arXiv (Cornell University) · 2026
- BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference
arXiv (Cornell University) · 2026
- MOSAIC: A Workload-Driven Simulation and Design-Space Exploration Framework for Heterogeneous NPUs
arXiv (Cornell University) · 2026
- GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units
2025
- GraNNite: Enabling High-Performance Execution of Graph Neural Networks on Resource-Constrained Neural Processing Units
arXiv (Cornell University) · 2025
- XAMBA: Enabling Efficient State Space Models on Resource-Constrained Neural Processing Units
arXiv (Cornell University) · 2025
- SecuPilot: A Security Coprocessor-Integrated Platform for Autonomous UAV Security
ACM Transactions on Embedded Computing Systems · 2025
- Demo Abstract: ECO: Low Power Context-Aware Multimodal AI on NPUs
2025
- Towards Efficient Acceleration of Hyena and Kolmogorov–Arnold Networks on NPUs
2025
- Toward Energy-Efficient Collaborative Inference Using Multisystem Approximations
IEEE Internet of Things Journal · 2024
- HARVEST: Towards Efficient Sparse DNN Accelerators using Programmable Thresholds
2024
- Towards Energy-Accuracy Scalable Multimodal Cognitive Systems
IEEE Embedded Systems Letters · 2024
- Energy-Efficient Approximate Edge Inference Systems
ACM Transactions on Embedded Computing Systems · 2023
- Efficient Hardware Acceleration of Emerging Neural Networks for Embedded Machine Learning: An Industry Perspective
2023
- arXiv (Cornell University)×8
- ACM Transactions on Embedded Computing Systems×7
- IEEE Transactions on Very Large Scale Integration (VLSI) Systems×5
- IEEE Transactions on Multi-Scale Computing Systems×2
- IEEE Embedded Systems Letters×2
- Lei Wang
Engineering · The Ohio State University
- Jung-Hoon Kim
Engineering · Purdue University West Lafayette
- Walter D. Leon-Salas
Engineering · Purdue University West Lafayette
- Jianping Zeng
Computer Science · Purdue University West Lafayette
- Gaurav Kumar K
Engineering · Purdue University West Lafayette
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 20, 2026.
Claim or correct this profile