Publications

2026

VLMSysTrojan: Stealthy System-Aware Backdoor Attacks Against Vision-Language Models
Yezheng Cheng, Zexin Li, Jiaqi Wu, Zhihong Zhang, Simin Chen
ECCV'26
ECCV'26
TetraRL: A Self-Adaptive Runtime for On-Device Deep Reinforcement Learning Systems
Zexin Li, Soheil Shirvani, Cong Liu
In Submission to TC
In Submission to TC
Orion: Enabling Self-adaptive Memory Management for On-device Online Continual Learning
Zexin Li, Nikil Dutt, Cong Liu
In Submission to TECS
In Submission to TECS [PDF] [BibTeX]
MIMONet: Multi-Input Multi-Output On-Device Deep Learning
Zexin Li, Xiaoxi He, Yufei Li, Wei Yang, Lothar Thiele, Cong Liu
In Submission to TECS
In Submission to TECS [PDF] [BibTeX]
TreeDiff: AST-Guided Code Generation with Diffusion LLMs
Yiming Zeng, Jinghan Cao, Zexin Li, Yiming Chen, Tao Ren, Zhuochun Li, Dawei Xiang, Xidong Wu, Shangqian Gao, Tingting Yu
ACL'26 Workshop
ACL'26 Workshop [PDF] [BibTeX]
NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models
Yiming Chen, Zexin Li, Xianghu Yue, Robby T. Tan, Haizhou Li
ACL'26
ACL'26 [BibTeX]
HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks
Yiming Zeng, Jinghan Cao, Zexin Li, Wanhao Yu, Zhankai Ye, Dawei Xiang, Ting Hua, Xin Liu, Shangqian Gao, Tingting Yu
ACL'26 findings
ACL'26 findings [PDF] [BibTeX]
Mixtraining: A Better Trade-Off Between Compute and Performance
Zexin Li*, Jiancheng Zhang*, Yufei Li, Yinglun Zhu, Cong Liu
TMLR
TMLR [PDF] [BibTeX]
RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics
Zexin Li, Tao Ren, Johnathan Liu, Xiaoxi He, Cong Liu
In Submission to TECS
In Submission to TECS [PDF] [BibTeX]
PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning
Zexin Li, Ziliang Zhang, Hyoseung Kim, Cong Liu
In Submission to TECS
In Submission to TECS [PDF] [BibTeX]

2025

LeMix: Unified Scheduling for LLM Training and Inference on Multi-GPU Systems
Yufei Li, Zexin Li, Yinglun Zhu, Cong Liu
RTSS'25 🌟 Outstanding Paper Award
RTSS'25 🌟 Outstanding Paper Award [PDF] [BibTeX]
Collaborative Learning in Agentic Systems: A Collective AI is Greater Than the Sum of Its Parts
Saptarshi Nath, Christos Peridis, Eseoghene Benjamin, Xinran Liu, Soheil Kolouri, Peter Kinnell, Zexin Li, Cong Liu, Shirin Dora, Andrea Soltoggio
AAAI'26
AAAI'26 [PDF] [BibTeX]
Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation
Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, Baishakhi Ray
EMNLP'25
EMNLP'25 [PDF] [BibTeX]
FineEdit: Unlock Instruction-Based Text Editing for LLMs
Yiming Zeng, Wanhao Yu, Zexin Li, Tao Ren, Yu Ma, Jinghan Cao, Xiyan Chen, Tingting Yu
EMNLP'25 findings
EMNLP'25 findings [PDF] [BibTeX]

2024

DuoJoule: Accurate On-Device Deep Reinforcement Learning for Energy and Timeliness
Soheil Shirvani, Aritra Samanta, Zexin Li, Cong Liu
RTSS'24
RTSS'24 [PDF] [BibTeX]
BOXR: Body and head motion Optimization framework for eXtended Reality
Ziliang Zhang, Zexin Li, Hyoseung Kim, Cong Liu
RTSS'24
RTSS'24 [PDF] [BibTeX]
Transferable Adversarial Attacks against ASR
Xiaoxue Gao, Zexin Li, Yiming Chen, Cong Liu, Haizhou Li
IEEE SPL
IEEE SPL [PDF] [BibTeX]
DeciX: Explain Deep Learning Based Code Generation Applications
Simin Chen, Zexin Li, Wei Yang, Cong Liu
FSE'24
FSE'24 [PDF] [BibTeX]
Genie: Smart ROS-based Caching for Connected Autonomous Robots
Zexin Li, Soroush Bateni, Cong Liu
Arxiv
Arxiv [PDF] [BibTeX]

2023

RT-LM: Uncertainty-Aware Resource Management for Real-Time On-Device Language Models
Yufei Li, Zexin Li, Wei Yang, Cong Liu
RTSS'23
RTSS'23 [PDF] [BibTeX]
RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics
Zexin Li, Tao Ren, Xiaoxi He, Cong Liu
RTSS'23
RTSS'23 [PDF] [BibTeX]
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics
Zexin Li, Aritra Samanta, Yufei Li, Andrea Soltoggio, Hyoseung Kim, Cong Liu
RTSS'23
RTSS'23 [PDF] [BibTeX]
PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas
Shahab Nikkhoo, Zexin Li, Aritra Samanta, Yufei Li, Cong Liu
IROS'23
IROS'23 [PDF] [BibTeX]
White-Box Multi-Objective Adversarial Attack on Dialogue Generation
Yufei Li, Zexin Li, Yingfan Gao, Cong Liu
ACL'23
ACL'23 [PDF] [BibTeX]
Dynamic Transformers Provide a False Sense of Efficiency
Yiming Chen, Simin Chen, Zexin Li, Wei Yang, Cong Liu, Robby Tan, Haizhou Li
ACL'23
ACL'23 [PDF] [BibTeX]
Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition
Zexin Li*, Bangjie Yin, Taiping Yao, Junfeng Guo, Shouhong Ding, Simin Chen, Cong Liu
CVPR'23
CVPR'23 [PDF] [BibTeX]

2021

Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time
Zexin Li, Yuqun Zhang*, Ao Ding, Husheng Zhou, Cong Liu
JSA
JSA [PDF] [BibTeX]