Yimeng Liu

I am a Ph.D. candidate in Computer Science and Engineering at Michigan State University, advised by Zhichao Cao.

I study how intelligent systems understand the physical world from incomplete observations. My published work builds on multimodal sensing and learning in real environments. Before MSU, I studied mathematics at Virginia Tech and worked on biomimetic sonar with Rolf Müller.

Current focus

My long-term direction is spatial intelligence: turning partial physical observations into reliable, persistent understanding for reasoning and action.

CVScholarPublicationsGitHubEmail
Yimeng Liu

2023 —Ph.D. candidate, Computer Science and EngineeringMichigan State University

2019 — 2023B.S., MathematicsVirginia Tech

Core papers & research

Selected work that shaped my current research direction.

  1. Manuscript

    SPIRIT: Sparse Physics-Informed Inverse Rendering for SAR Imaging

    Unpublished research manuscript

  2. Manuscript

    Mímir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control

    Unpublished research manuscript

  3. 2026arXiv'26

    AIoT-Based Continuous, Contextualized, and Explainable Driving Assessment for Older Adults

    Yimeng Liu, Fangwei Zhang, Maolin Gan, Jialuo Du, Jingkai Lin, Yawen Wang, Fei Sun, Honglei Chen, Linda Hill, Ruofeng Liu, Tianxing Li, Zhichao Cao

    arXiv preprint arXiv:2603.00691 (2026)

  4. 2025SenSys'25

    Proteus: Enhanced mmWave Leaf Wetness Detection with Cross-Modality Knowledge Transfer

    Yimeng Liu, Maolin Gan, Huaili Zeng, Yidong Ren, Gen Li, Jingkai Lin, Younsuk Dong, Xiaobo Tan, Zhichao Cao

    Proceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems (2025)

  5. 2025INFOCOM'25

    Adonis: Neural-Enhanced Fine-Grained Leaf Wetness Sensing with Efficient mmWave Imaging

    Yimeng Liu*, Maolin Gan*, Gen Li, Younsuk Dong, Zhichao Cao

    IEEE INFOCOM 2025 — IEEE Conference on Computer Communications (2025) · Co-first author

  6. 2024MobiCom'24

    Hydra: Accurate Multi-Modal Leaf Wetness Sensing with mm-Wave and Camera Fusion

    Yimeng Liu, Maolin Gan, Huaili Zeng, Li Liu, Younsuk Dong, Zhichao Cao

    Proceedings of the 30th Annual International Conference on Mobile Computing and Networking (2024)

Publications & Research resourcesServiceFull timeline

Academic service & community

Service

Program committee

  • IEEE DSAA 2025

Invited reviewer

  • UbiComp / ISWC · UbiSense 2025
  • IEEE Internet of Things Journal
  • IEEE Transactions on Mobile Computing
  • IEEE Internet Computing
  • HAI 2025 · Poster track

Conferences & talks

  • 2025 · Irvine, CAACM SenSysPresented Proteus
  • 2024 · Washington, D.C.ACM MobiComPresented Hydra
  • 2024 · Purdue UniversityNSF Workshop on Sustainable ComputingParticipant
  • Invited talk, University of Hawai'i at Mānoa — October 2024
All activities

Recent updates

  1. Our driving assessment preprint discusses continuous, contextualized and explainable assessment for older adults.

  2. My journey from math to computing was highlighted by MSUTODAY.

  3. The Hydra-Bench multimodal leaf-wetness benchmark preprint is publicly available.

Full timeline

How I approach research

Start with the question, not the model.
Define what must be understood or decided before choosing how to model it.
Keep the observation in view.
Ask what the evidence supports, what it cannot distinguish, and which assumptions connect observation to physical state.
Test where the assumption breaks.
Evaluate where a system works, where its assumptions fail, and whether it can recognize when the evidence is no longer sufficient.

Further reading What changes between a measurement and understanding?

My research vision

I aim to build intelligent systems that turn partial physical observations into persistent, reliable understanding—and use it to reason and act under uncertainty. I see spatial intelligence as this full loop: observing the world, forming and updating representations of it, and knowing when those representations can support action.

What can we know from incomplete evidence?

How can heterogeneous observations be connected to physical state while keeping uncertainty explicit?

How should understanding change over time?

How can a system preserve, revise or discard what it believes as observations and conditions change?

When is understanding reliable enough to act?

How should uncertainty, consequences and missing evidence determine whether a system acts, gathers more information or defers?

Research direction & roadmap

Get in touch

I welcome conversations about multimodal sensing, physical representations and reliable intelligent systems, especially where these questions meet a concrete measurement problem.

liuyime2@msu.edu

CVService