Ciem Cornelissen

IDLab, Department of Information Technology

Ghent University - imec

Ghent, Belgium

I am a PhD researcher at IDLab, Department of Information Technology at Ghent University - imec, where I specialize in adaptive sensor fusion for autonomous systems with applications in precision agriculture and environmental monitoring. My research focuses on developing robust AI-driven perception systems that bridge fundamental machine learning innovation with real-world deployment challenges.

My academic journey reflects a deliberate progression from fundamental science to applied AI. I completed my Bachelor’s and Master’s in Physics at Ghent University, where I developed strong analytical foundations and an aptitude for dissecting complex problems at their core. During my physics master’s, elective courses in artificial intelligence sparked a passion that led me to pursue an Advanced Master’s in Artificial Intelligence at KU Leuven (2023), where I specialized in deep learning, computer vision, and data science. This trajectory has uniquely positioned me to tackle the multi-modal sensor fusion challenges central to my PhD research.

My current research centers on the synergistic combination of Hyperspectral Imaging (HSI), RGB and SWIR sensors, Unmanned Aerial Vehicles (UAVs), and Deep Learning; particularly transformer-based architectures. I develop end-to-end systems that transform raw multi-modal sensor data from autonomous platforms into actionable insights. A key focus is making these AI systems practically deployable in uncontrolled field environments by addressing challenges like variable illumination, limited computational resources on edge devices, spectral-spatial trade-offs, and the need for real-time processing.

Key Research Contributions:

Developed LISA (Light-Invariant Spectral Autoencoder), a domain-adversarial deep learning framework enabling robust, non-destructive grape quality assessment under varying illumination, part of a complete IoT-enabled robotic system for precision viticulture
Created OHSLIC (Online Hyperspectral Simple Linear Iterative Clustering), an efficient algorithm achieving real-time phenotype segmentation on resource-constrained UAVs through adaptive, on-device processing
Co-authored research on computational fairness in adaptive neural networks, introducing resource allocation disparities as a novel dimension of algorithmic fairness and highlighting ethical considerations in efficiency-driven AI
Developed Le MuMo JEPA, a multi-modal self-supervised framework that learns unified RGB-LiDAR-thermal representations through learnable fusion tokens, achieving strong performance-efficiency trade-offs on Waymo, nuScenes, and FLIR benchmarks

My work has been published in leading venues including the IEEE Internet of Things Journal, IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), and Neural Computing and Applications. Beyond research, I serve as a Teaching Assistant for the Reinforcement Learning course at Ghent University (2024-2026) and supervise master’s thesis students on topics spanning hyperspectral imaging, deep learning for precision agriculture, and multi-modal sensor fusion.

I am driven by a deep fascination with AI’s transformative potential for autonomous systems, particularly in optimizing real-time perception through adaptive sensor fusion. My research philosophy centers on identifying fundamental deployment barriers in real-world environments and developing innovative, domain-invariant solutions that advance both the theoretical foundations and practical applicability of AI-driven perception systems.

news

Mar 26, 2026	New paper accepted at CVPR 2026 URVIS Workshop! Our work on Le MuMo JEPA — a multi-modal self-supervised framework for learning unified RGB-LiDAR-thermal representations with learnable fusion tokens — has been accepted!
Oct 20, 2025	New blog post published! Read about our illumination-invariant AI system for in-field grape quality mapping.
Oct 15, 2025	Deep Dive Talk at FAIR Day 2025
Oct 03, 2025	New paper published in IEEE Internet of Things Journal! Our work on illumination-invariant deep learning for in-field grape yield and quality mapping is now available.
Jun 30, 2025	New publication in Neural Computing and Applications! Our research on computational fairness in adaptive neural networks explores resource allocation disparities across demographic subgroups.

latest posts

Oct 20, 2025	In-Field Grape Quality Mapping with Illumination-Invariant AI

selected publications

2026

CVPR
Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens

Ciem Cornelissen, Sam Leroux, and Pieter Simoens

In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops - URVIS, 2026

Abs Bib PDF

A self-supervised framework that learns unified representations from RGB images and aligned companion modalities. Extends LeJEPA to the multi-modal setting by learning fusion tokens that act as a latent bottleneck between modality-specific patch stems inside a shared transformer. Evaluated on Waymo, nuScenes, and RGB-thermal FLIR benchmarks, demonstrating strong performance-efficiency trade-offs for detection, depth estimation, and segmentation.
@inproceedings{cornelissen2026lemumojepa, title = {Le MuMo JEPA: Multi-Modal Self-Supervised Representation Learning with Learnable Fusion Tokens}, author = {Cornelissen, Ciem and Leroux, Sam and Simoens, Pieter}, booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops - URVIS}, year = {2026}, }

2025

IEEE IoT
In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning

Ciem Cornelissen, Sander De Coninck, Axel Willekens, and 2 more authors

IEEE Internet of Things Journal, 2025

Abs Bib PDF

Development of the LISA framework for illumination-invariant hyperspectral imaging analysis in precision viticulture. An end-to-end IoT-enabled robotic system for non-destructive, real-time mapping of grape yield and quality.
@article{cornelissen2025vineyard, title = {In-Field Mapping of Grape Yield and Quality with Illumination-Invariant Deep Learning}, author = {Cornelissen, Ciem and De Coninck, Sander and Willekens, Axel and Leroux, Sam and Simoens, Pieter}, journal = {IEEE Internet of Things Journal}, year = {2025}, }
WACV
Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data

Ciem Cornelissen, Sam Leroux, and Pieter Simoens

In IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops, 2025

Abs Bib PDF

Introduction of the OHSLIC algorithm for computationally efficient, real-time phenotype segmentation from hyperspectral imaging data. Enables on-device processing on UAVs.
@inproceedings{cornelissen2025ohslic, title = {Adaptive Clustering for Efficient Phenotype Segmentation of UAV Hyperspectral Data}, author = {Cornelissen, Ciem and Leroux, Sam and Simoens, Pieter}, booktitle = {IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) Workshops}, year = {2025}, }
NCA
Computational Fairness in Adaptive Neural Networks

Sam Leroux, Ciem Cornelissen, Vishisht Sharma, and 1 more author

Neural Computing and Applications, 2025

Abs Bib

A novel investigation into the fairness of adaptive neural networks, analyzing disparities in computational resource allocation across demographic subgroups. Introduces computational resource allocation as a new dimension of AI fairness.
@article{cornelissen2025fairness, title = {Computational Fairness in Adaptive Neural Networks}, author = {Leroux, Sam and Cornelissen, Ciem and Sharma, Vishisht and Simoens, Pieter}, journal = {Neural Computing and Applications}, year = {2025}, }

2023

Quantum Computing for Earth Observation

Ciem Cornelissen

KU Leuven, 2023

Abs Bib PDF

Master’s thesis in Artificial Intelligence exploring the application of quantum computing techniques to Earth observation and remote sensing challenges.
@mastersthesis{cornelissen2023quantum, title = {Quantum Computing for Earth Observation}, author = {Cornelissen, Ciem}, year = {2023}, school = {KU Leuven}, }

2022

Criticality and Forecasting of the Cryptocurrency Market

Ciem Cornelissen

Ghent University, 2022

Abs Bib PDF

Master’s thesis in Physics applying advanced computational and statistical methods to model complex, non-linear, and stochastic systems in financial markets.
@mastersthesis{cornelissen2022crypto, title = {Criticality and Forecasting of the Cryptocurrency Market}, author = {Cornelissen, Ciem}, year = {2022}, school = {Ghent University}, }