About Me
I am a Ph.D. researcher at Delft University of Technology working on Embedded AI and TinyML systems. My research focuses on understanding and optimizing deep learning workloads on resource-constrained microcontrollers from a system-level perspective.
Current research topics:
instruction-level profiling of neural networks on MCUs,
energy and latency modeling,
split inference,
and end-to-end optimization of embedded AI systems.
Publications
indicates first author.
InstMeter: An Instruction-Level Method to Predict Energy and Latency of DL Model Inference on MCUs
, Qing Wang, Marco Zuniga.ACM MobiCom 2026 (CORE A*, CCF A)
Introduces the first instruction-level modeling framework to accurately predict
energy consumption and latency of TinyML inference on microcontrollers.
