Tomoyoshi Kimura picture
Tomoyoshi Kimura
CS Ph.D. @ UIUC
ABOUT
I am a Ph.D. student in Computer Science at the University of Illinois at Urbana-Champaign (UIUC), where I am fortunate to work with Prof. Tarek Abdelzaher in the Coordinated Science Laboratory. My research focuses on building intelligent sensing systems by developing efficient learning frameworks for multimodal time-series signals, with an emphasis on Edge AI and self-supervised representation learning for Internet of Things (IoT) applications. I previously earned both my Master of Science and Bachelor of Science in Computer Science from UIUC.

I’m looking for self-driven students who are excited about AI for IoT sensing applications. I’m also happy to chat about research paths, project experiences, or academic programs at UIUC. If you’d like to connect, please fill out this form to set up a private chat 🙂
RESEARCH INTERESTS
My research centers on advancing sensing-driven intelligence through multimodal time-series learning, reasoning, and human-centric design. I develop self-supervised methods that can extract rich representations from diverse sensing modalities, enabling machines to interpret complex physical-world signals with higher robustness and deeper semantic understanding. I am particularly interested in building sensing-driven reasoning frameworks that move beyond simple pattern recognition toward cognitive-level inference. At the same time, I focus on designing interpretable, reliable, and human-centric sensing solutions that work in real-world environments. Last but not least, I explore data-efficient and computationally lightweight foundation models that make large-scale sensing intelligence practical for deployment on edge and embedded devices.
1. Multimodal Time-Series Learning:
Self-supervised representation learning for multi-modal time-series sensing signals.
2.Sensing Reasoning:
Sensing-driven intelligence with advanced reasoning capabilities in the physical world.
3.Human-Centric Sensing:
Robust and interpretable sensing systems for real-world human-centric applications.
4.Efficient Foundation Models:
Smart sensing with data-efficient training and lightweight deployment for real-world systems.
RECENT UPDATES
[2025]Papers accepted to NeurIPS, AIoT, CogMI, MASS, Sensys, ACM The Web, DCOSS, ICCCN, Smartcomp.
[2025.08]Started as a Ph.D. student in Computer Science at UIUC.
[2024]Papers accepted to InfoCom 2025, IMWUT 2025, NeurIPS, Sensys, MASS, ICCCN, FMSys, ACM Web.
[2024.12]Graduated from UIUC with M.S. in Computer Science.
Thesis: 'Towards Micro Foundation Models for Robust Multimodal IoT Sensing'.
[2024.12]Tutorial on 'Machine Learning and Foundation Models for Sensing Applications' at Secon 2024.
[2023]One paper accepted to NeurIPS.
[2023.08]Joined UIUC as a MSCS student.
[2023.05]Graduated from UIUC with B.S. in Computer Science with Highest Honors.