About me

I am an Assistant Professor in the Electrical andmComputer Engineering department at San Diego State University, and director of the Efficient Computing Systems (ECS) Laboratory. After studying Computer Enginnering at Politecnico di Torino in Italy, I obtained my PhD degree in Electrical and Electronic Engineering from École Polytechnique Fédérale de Lausanne, Switzerland, in 2023. After my graduation, I worked at the SEELab at UC San Diego as a postdoctoral scholar for one year and then joined San Diego State University as a faculty memeber in 2025. My research interests include HW-SW co-design optimizations for edge AI, unsupervised, ensemble, and distributed learning, space computing, and processing in-memory acceleration on emerging memory technologies.

News

• 2026 - August. We studied how ensembles of CNNs can be used in distributed learning to limit training energy and communication overhead. I'm extremely happy to share that our paper titled "DELEA: Distributed Ensemble Learning for Energy-Efficient IoT Applications" just got accepted at MSWiM'26 and will presented in Paris this October! Another good result from Yi-Yang and my two PhD students, Kaila and Ben!


• 2026 - August. Ben developed a autoregressive framework based on hyperdimensional computing to predict future satellite anomalies from the analysis of telemetry data. His work titled "Early Detection of Satellite Telemetry Data Anomalies using Hyperdimensional Computing" will be presented soon at SPAICE 2026 🚀. Great work, Ben!


• 2026 - March. Our novel work on Bayesian optimization for HW-SW co-design titled "Constraint-Scheduled Bayesian Optimization for Software-Hardware Co-Optimization on HDnn-PIM" has just been accepted at ES Letters 2026 🚀. Congratulations to Chien-Yi and our Intel collaborators for this great work!


• 2026 - March. I'm happy to share that our new work on vision transformers acceleration "AA-DiT: An Algorithm-Architecture Co-Design for Diffusion Transformer Acceleration" has been accepted at TCAD 2026. Great work, Siqi!


• 2026 - February. I'm happy to share that our new paper titled "HyperLiDAR: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing" has been accepted at DAC 2026 🚀. Congratulations to amazing Ivannia, Yi, Ye, and all the authors for this amazing work!


• 2026 - January. Our new paper "SIMCH: Stochastic In-Memory Computing Using High-Density MTJ" has been accepted at ISCAS 2026! Great work done in collaboration with UCSD and MIT!


• 2025 - December. I am honored to share that I have been awarded the 2026 SEED funds for the project "Multi-constraint Hardware-Software co-optimization of In-Memory Hyperdimensional Computing for Edge AI"


• 2025 - November. Our new paper titled "Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANNS Systems" has been accepted at DATE 2026 🚀. Congratulations to amazing Tianqi Zhang for his great work!


• 2025 - August. I am currently looking for a highly motivated PhD student starting Fall 2026!!!
  For more info click here


• 2025 - August. I am excited to join San Diego State University as Assistant Professor in the Dept. of ECE

Research Interests

I am interested in energy-efficient design and HW-SW co-optimization for both ultra-low-power IoT systems and large-scale applications. My current key research directions include:

• HW-SW co-design for Efficient AI systems


• Distributed, Unsupervised, and Continual Learning


• Processing-in-memory acceleration


• Autonomous AI-based space operations

Courses

• COMPE 271. Computer Organization
• COMPE 361. Advanced Programming

Selected Publications

• Tianqi Zhang, Flavio Ponzina, and Tajana Rosing “TRQ - Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANN Systems”, DATE, 2026


• Flavio Ponzina, Sumukh Pinge, Zheyu Li, Abhijay Deevi, Yilin Ge, Mingu Kang, and Tajana Rosing “SmartMS - Efficient Hierarchical Database Search for Mass Spectrometry via Processing-in-Memory”, ISLPED, 2025


• Le Zhang, Onat Gungor, Flavio Ponzina, and Tajana Rosing., “E-QUARTIC: Energy Efficient Edge Ensemble of Convolutional Neural Networks for Resource-Optimized Learning”, ASP-DAC, 2025


• Kumar Ashwani, Yucheng Zhou, Sai Praneeth Potladurthy, Jeoghoon Kim, Weihong Xu, Flavio Ponzina, Seounghyun Kim, Ertugrul Cubukcu, Tajana Rosing, Gert Cauwenbergh, and Duygu Kuzum. “Filament-free Bulk RRAM with High Endurance and Long Retention for Neuromorphic Few-Shot Learning On-Chip”, IEDM, 2024


• Flavio Ponzina, Rishikanth Chandrasekaran, Anya Wang, Seiji Minowada, Siddharth Sharma, and Tajana Rosing. “Multi-Model Inference Composition of Hyperdimensional Computing Ensembles”, ICCD, 2024


• Keming Fan, Ashkan Moradifirouzabadi, Xiangjin Wu, Zheyu Li, Flavio Ponzina, Anton Persson, Vikram Adve, Eric Pop, Tajana Rosing, and Mingu Kang. “SpecPCM: A Low-power PCM-based In-Memory Computing Accelerator for Full-stack Mass Spectrometry Analysis” IEEE JXCDC, 2024.


• Flavio Ponzina, Mialyssa Gomez, Congge Xu, and Tajana Rosing. “GlucoseHD Predicting Glucose Levels using Hyperdimensional Computing”, IEEE Design and Test, 2024.


• Marco Rios, Flavio Ponzina, Alexandre Levisse, Giovanni Ansaloni, and David Atienza. "Bit-line computing for CNN accelerators co-design in edge AI inference" IEEE Transactions on Emerging Topics in Computing 11, no. 2, 2023.


• Marco Rios, Flavio Ponzina, Giovanni Ansaloni, Alexandre Levisse, and David Atienza. "Running efficiently cnns on the edge thanks to hybrid sram-rram in-memory computing", DATE, 2021


• Flavio Ponzina, Miguel Peon-Quiros, Andreas Burg, and David Atienza. "E2cnns: Ensembles of convolutional neural networks to improve robustness against memory errors in edge-computing devices" IEEE Transactions on Computers 70, no. 8, 2021.