Zexin Li

Zexin Li

Ph.D. Student of ECE

The University of California, Riverside

I am a Ph.D. student at the University of California, Riverside (UCR). I am fortunate to be advised by Dr. Cong Liu . I received a bachelor’s degree from the Southern University of Science and Technology (SUSTech) under the advice of Dr. Yuqun Zhang in July 2020. My research interests lie in interdisciplinary fields of real-time embedded systems and on-device machine learning.

I am actively looking for cooperation in the following topics: (1) deploying machine learning models on real-time embedded devices, (2) system-application co-optimization of machine learning systems, and (3) improving performance robustness in machine learning systems.

I am on job market now! I am currently on the 2025-2026 job market and open to opportunities in real-time embedded systems, on-device machine learning, cyber-physical systems, AI/ML, and embedded intelligent systems research. I welcome conversations with teams working on cutting-edge machine learning systems and embedded intelligent systems workflows. Feel free to reach out at 📧 [email protected] if you believe there might be a fit.

Feel free to contact me if we share common research interests.

Download my Curriculum Vitae .

News

04/2026 - Two papers are accepted by ACL'26 .
03/2026 - One paper is accepted by TMLR .
12/2025 - Our RTSS'25 paper received Outstanding Paper Award.
11/2025 - One paper is accepted by AAAI'26 .
08/2025 - Two papers are accepted by EMNLP'25 .
07/2025 - One paper is accepted by RTSS'25 .
08/2024 - One paper is accepted by IEEE Signal Processing Letters .
07/2024 - Two papers are accepted by RTSS'24 .
04/2024 - One paper is accepted by FSE'24 .
03/2024 - Pass the qualification exam of Ph.D. at UCR .
07/2023 - Three papers are accepted by RTSS'23 .
06/2023 - One paper is accepted by IROS'23 .
05/2023 - Two papers are accepted by ACL'23 .
02/2023 - One paper is accepted by CVPR'23 .
09/2022 - Honored to receive the Dean’s Distinguished Fellowship, UCR.
09/2022 - Join UCRiverside and Dr. Cong Liu ’s Autonomous Embedded Systems Lab in 2022 Fall.
01/2022 - Pass the qualification exam of Ph.D. at UTDallas .
01/2022 - Join UTDallas and Dr. Cong Liu ’s Real-Time System Lab in 2022 Spring.
05/2021 - Begin the research intern in Tecent Youtu Lab , Shanghai, China.
04/2021 - Admitted into Tencent Rhino Bird Elite Talent Training Program .
03/2021 - One paper is accepted by JSA , great thanks to Dr. Yuqun Zhang .
10/2019 - Begin the research intern in Kuaishou , Shenzhen, China.

Publications

2026

TreeDiff: AST-Guided Code Generation with Diffusion LLMs
In ACL'26 Workshop
HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
In ACL'26 findings
NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models
In ACL'26
Mixtraining: A Better Trade-Off Between Compute and Performance
In TMLR
PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas
In Submission to TECS
RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
In Submission to TCPS

2025

LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems
In RTSS'25 🌟 Outstanding Paper Award
Collaborative Learning in Agentic Systems: A Collective AI is Greater Than the Sum of Its Parts
In AAAI'26
FineEdit: Unlock Instruction-Based Text Editing for LLMs
In EMNLP'25 findings
Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation
In EMNLP'25

2024

BOXR: Body and head motion Optimization framework for eXtended Reality
In RTSS'24
DuoJoule: Accurate On-Device Deep Reinforcement Learning for Energy and Timeliness
In RTSS'24
Transferable Adversarial Attacks against ASR
In IEEE SPL
DeciX: Explain Deep Learning Based Code Generation Applications
In FSE'24
Genie: Smart ROS-based Caching for Connected Autonomous Robots
In Arxiv

2023

RT-LM: Uncertainty-Aware Resource Management for Real-Time On-Device Language Models
In RTSS'23
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
In RTSS'23
RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
In RTSS'23
MIMONet: Multi-Input Multi-Output On-Device Deep Learning
In Arxiv
PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas
In IROS'23
Dynamic Transformers Provide a False Sense of Efficiency
In ACL'23
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
In ACL'23
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
In CVPR'23

2021