Josse Van Delm

  • Compilers
  • Processor Architectures
  • Heterogeneous Accelerator Systems
  • Embedded Machine Learning
  • Open-source Hard- and Software
Josse Van Delm
Josse Van Delm
Phd student
Hardware-efficient AI and ML
+3216710461
josse.vandelm@esat.kuleuven.be
Marian Verhelst
Or meet the full MICAS team

Current research topic

Career overview

Josse Van Delm was born in Antwerp, Belgium in 1997.

In 2019 he received the M.Sc. degree in Electronics Engineering Technology from KU Leuven De Nayer campus in Sint-Katelijne-Waver, Belgium. The title of his Master's thesis was "RGB-to-Thermal Image Transformation using Generative Neural Networks".
In 2021 he received the M.Sc. degree in Electrical Engineering from KU Leuven, Belgium. The title of his second Master's thesis was "Deep Learning Compiler for Hardware Accelerators and Embedded Devices".

Josse is very passionate about open-source hard- and software. In the summers of 2019 and 2020 he was with Open Knowledge Belgium's Open Summer of Code.

Currently, he is a research assistant at MICAS where he is working towards a PhD degree on compilers for AI accelerators, under the guidance of Prof. dr. ir. Marian Verhelst.

Publications

The Configuration Wall: Characterization and Elimination of Accelerator Configuration Overhead Josse Van Delm, Anton Lydike, Joren Dumoulin, Jonas Crols, Xiaoling Yi, Ryan Antonio, Jackson Woodruff, Tobias Grosser, and Marian Verhelst · Conference Proceeding · Jan 1. 2026 PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON ARCHITECTURAL SUPPORT FOR PROGRAMMING LANGUAGES AND OPERATING SYSTEMS, VOL 1, ASPLOS 2026; 2026; pp. 265 - 280
MATCH: Model-Aware TVM-Based Compilation for Heterogeneous Edge Devices Mohamed Amine Hamdi, Francesco Daghero, Giuseppe Maria Sarda, Josse Van Delm, Arne Symons, Luca Benini, Marian Verhelst, Daniele Jahier Pagliari, and Alessio Burrello · Article · Apr 1. 2025 IEEE Transactions On Computer-Aided Design Of Integrated Circuits And Systems; 2025; Vol. 44; iss. 10; pp. 3844 - 3857
HTVM: Efficient Neural Network Deployment On Heterogeneous TinyML Platforms Josse Van Delm, Maarten Vandersteegenl, Alessio Burrello, Giuseppe Maria Sarda, Francesco Conti, Daniele Jahier Pagliari, Luca Benini, and Marian Verhelst · Conference Proceeding · Jan 1. 2023 2023 60TH ACM/IEEE DESIGN AUTOMATION CONFERENCE, DAC; 2023; pp.

Awards & honors

  • Recipient of FWO Strategic Basic Fellowship (2022)

Teaching

Digitale Elektronica En Processoren (B-KUL-H01L1A)