Zexin Li

Orcid: 0000-0001-8758-2151

Affiliations:
  • The University of California, Riverside, CA, USA
  • Southern University of Science and Technology, Shenzhen, China (former)


According to our database1, Zexin Li authored at least 27 papers between 2021 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
RED: Adaptive Real-Time DAG Scheduling for Robotic Inference under Environmental Dynamics.
CoRR, May, 2026

PIMbot: A Self-Adaptive Attack Framework for Adversarial Manipulation of Multi-Robot Reinforcement Learning.
CoRR, May, 2026

MORE: Multi-Objective Adversarial Attacks on Speech Recognition.
CoRR, January, 2026

NaturalSloth: Revisiting Denial-of-Service Attacks on Large Language Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Policy Search, Retrieval, and Composition via Task Similarity in Collaborative Agentic Systems.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
HyperEdit: Unlocking Instruction-based Text Editing in LLMs via Hypernetworks.
CoRR, December, 2025

TreeDiff: AST-Guided Code Generation with Diffusion LLMs.
CoRR, August, 2025

Collaborative Learning in Agentic Systems: A Collective AI is Greater Than the Sum of Its Parts.
CoRR, June, 2025

Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation.
CoRR, February, 2025

Lemix: Unified Scheduling for Llm Training and Inference on Multi-Gpu Systems.
Proceedings of the IEEE Real-Time Systems Symposium, 2025

Bridging the Editing Gap in LLMs: FineEdit for Precise and Targeted Text Modifications.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

Benchmarking Large Language Models Under Data Contamination: A Survey from Static to Dynamic Evaluation.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Transferable Adversarial Attacks Against ASR.
IEEE Signal Process. Lett., 2024

DeciX: Explain Deep Learning Based Code Generation Applications.
Proc. ACM Softw. Eng., 2024

Genie: Smart ROS-based Caching for Connected Autonomous Robots.
CoRR, 2024

BOXR: Body and head motion Optimization framework for eXtended Reality.
Proceedings of the IEEE Real-Time Systems Symposium, 2024

DuoJoule: Accurate On-Device Deep Reinforcement Learning for Energy and Timeliness.
Proceedings of the IEEE Real-Time Systems Symposium, 2024

2023
R^3: On-device Real-Time Deep Reinforcement Learning for Autonomous Robotics.
CoRR, 2023

MIMONet: Multi-Input Multi-Output On-Device Deep Learning.
CoRR, 2023

RED: A Systematic Real-Time Scheduling Approach for Robotic Environmental Dynamics.
Proceedings of the IEEE Real-Time Systems Symposium, 2023

RT-LM: Uncertainty-Aware Resource Management for Real-Time Inference of Language Models.
Proceedings of the IEEE Real-Time Systems Symposium, 2023

$\mathrm{R}^{3}$: On-Device Real-Time Deep Reinforcement Learning for Autonomous Robotics.
Proceedings of the IEEE Real-Time Systems Symposium, 2023

PIMbot: Policy and Incentive Manipulation for Multi-Robot Reinforcement Learning in Social Dilemmas.
IROS, 2023

Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognition.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

White-Box Multi-Objective Adversarial Attack on Dialogue Generation.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

Dynamic Transformers Provide a False Sense of Efficiency.
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2021
Efficient algorithms for task mapping on heterogeneous CPU/GPU platforms for fast completion time.
J. Syst. Archit., 2021


  Loading...