Gianna Paulin

About

Gianna Paulin is a leading researcher in energy-efficient AI-IoT systems, with a focus on heterogeneous System-on-Chip (SoC) architectures for edge computing. Her work centers on developing ultra-low-power platforms that can run diverse workloads—from compute-intensive Deep Neural Networks (DNNs) to general-purpose tasks—within a power envelope of just tens of milliwatts. Paulin’s major contributions include the design of Marsellus and a 12.4 TOPS/W AI-IoT SoC, which integrate up to 16 RISC-V cores with precision-scalable DNN accelerators supporting 2-to-8-bit quantization. A standout innovation is her use of adaptive body biasing, which boosts energy efficiency by 30% under varying operating conditions. Her most-cited paper (34 citations) demonstrates a system achieving 136 GOPS at 12.4 TOPS/W, targeting applications like augmented reality and personalized healthcare. Paulin’s work bridges the gap between flexibility and extreme efficiency, making her a key figure in advancing nano-robotics and always-on AI at the edge.

Research Focus

Key Achievements

Top Papers

1. 1
   22.1 A 12.4TOPS/W @ 136GOPS AI-IoT System-on-Chip with 16 RISC-V, 2-to-8b Precision-Scalable DNN Acceleration and 30%-Boost Adaptive Body Biasing

   34 citations · 2023
2. 2
   Marsellus: A Heterogeneous RISC-V AI-IoT End-Node SoC with 2-to-8b DNN Acceleration and 30%-Boost Adaptive Body Biasing

   2 citations · 2023

Key Collaborators

Contact & Links