Liangqi Yuan

Liangqi Yuan

PhD Student

Purdue University

Greetings! I am a PhD candidate in the School of Electrical and Computer Engineering at Purdue University, where I serve as a Graduate Research Assistant at the ION lab under the supervision of Prof. Christopher G. Brinton. Currently, I am a research intern at OPPO US Research Center, and I have previously completed a SWE internship at Meta. My research focuses on Efficient Multimodal LLMs and Inference Optimization.

Interests
  • Multimodal Learning
  • Mobile Computing
  • Large Language Models
Experience

  • Research Intern, Fall 2025

    OPPO US Research Center

  • SWE Intern, Summer 2025

    Meta

  • PhD in ECE, 2026

    Purdue University

News

Selected Publications

For a complete list of publications, please see Publications.
🔥 Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings
Compared to traditional machine learning models, recent large language models (LLMs) can exhibit multi-task-solving capabilities …
ACM International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (MobiHoc) 🏆 Best Paper Runner-Up Award October, 2025
PDF Cite DOI Code
🔥 Local-Cloud Inference Offloading for LLMs in Multi-Modal, Multi-Task, Multi-Dialogue Settings
🔥 Next-Generation LLM for UAV: From Natural Language to Autonomous Flight
With the rapid advancement of Large Language Models (LLMs), their capabilities in various automation domains, particularly Unmanned …
arXiv September, 2025
PDF Cite DOI Code Web
🔥 Next-Generation LLM for UAV: From Natural Language to Autonomous Flight
🔥 LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
The rise of large language models (LLMs) has made natural language-driven route planning an emerging research area that encompasses …
Empirical Methods in Natural Language Processin (EMNLP) August, 2025
PDF Cite DOI Code
🔥 LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences
🔥 Smart Pressure e-Mat for Human Sleeping Posture and Dynamic Activity Recognition
With the emphasis on healthcare, early childhood education, and fitness, non-invasive measurement and recognition methods have received …
IEEE Journal of Selected Areas in Sensors November, 2024
PDF Cite DOI
🔥 Smart Pressure e-Mat for Human Sleeping Posture and Dynamic Activity Recognition
🔥 Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?
Federated learning (FL) has become a cornerstone in decentralized learning, where, in many scenarios, the incoming data distribution …
arXiv November, 2024
PDF Cite DOI Code
🔥 Using Diffusion Models as Generative Replay in Continual Federated Learning -- What will Happen?
Decentralized Federated Learning: A Survey and Perspective
Federated learning (FL) has been gaining attention for its ability to share knowledge while maintaining user data, protecting privacy, …
IEEE Internet of Things Journal May, 2024
PDF Cite DOI
Decentralized Federated Learning: A Survey and Perspective
Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
Multimodal federated learning (FL) aims to enrich model training in FL settings where clients are collecting measurements across …
arXiv January, 2024
PDF Cite DOI Video Code
Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition
Naturalistic driving action recognition (NDAR) has proven to be an effective method for detecting driver distraction and reducing the …
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops June, 2023
PDF Cite Poster Slides DOI
Peer-to-Peer Federated Continual Learning for Naturalistic Driving Action Recognition
Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
Federated learning (FL) shines through in the internet of things (IoT) with its ability to realize collaborative learning and improve …
IEEE Internet of Things Journal May, 2023
PDF Cite DOI
Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application
Three Dimensional Indoor Positioning Based on Passive Radio Frequency Signal Strength Distribution
In recent years, indoor positioning systems (IPSs) have received attention from many research fields, such as robotics, navigation, …
IEEE Internet of Things Journal March, 2023
PDF Cite DOI
Three Dimensional Indoor Positioning Based on Passive Radio Frequency Signal Strength Distribution
Velostat Sensor Array for Object Recognition
This paper presents a cost-effective pressure sensing system for object detection and identification. The pressure sensing system …
IEEE Sensors Journal December, 2021
PDF Cite DOI
Velostat Sensor Array for Object Recognition

Presentations

Communication-Efficient Federated Learning for Multimodal Automatic Target Recognition
The 8th Annual Workshop on Naval Applications of Machine Learning (NAML 2024)
Mar 11, 2024 California, USA
Poster
Advancing Personalized Driver Action Recognition in Federated Learning: User-Centric Approaches
The 35th IEEE Intelligent Vehicles Symposium (IV 2023)
Jun 4, 2023 Alaska, USA
Slides IoT in ITS: IV2023 Workshop

Teaching

Purdue University

Grading Assistant

Professional Activities

Journal Reviewer

Technical Program Committee (TPC) Member/Reviewer

Proposal Reviewer

Contact