Hi there! I am a Ph.D. student in the EPIC Lab at Rensselaer Polytechnic Institute, advised by Prof. Liu Liu. I received my B.E. in Software Engineering from the University of Electronic Science and Technology of China. I am very fortunate to work with my advisor and labmates on impactful and exciting research problems. I have also closely collaborated with IBM and Samsung on projects related to trustworthy AI and memory efficiency-related machine learning.

Research Interests

My research interests lie in machine learning systems, software-hardware co-design, and trustworthy AI. I focus on building robust and efficient foundations for both vision models and large language models, including system-level optimization, architecture support, and robustness/safety alignment techniques.

News

  • [01/09/26] [Service] Served as a sub-reviewer of DAC'26.
  • [11/25/25] [Paper] Our paper on attention sparsity mapping on Process-In-Memory has been accepted to ASPLOS'26 ! Congrats to Zehao!
  • [09/03/25] [Service] Served as a reviewer of ICLR'26.
  • [06/30/25] [Paper] Our paper on Analog Compute-in-Memory has been accepted to ICCAD'25 ! Congrats to Yayue!
  • [12/11/24] [Service] Served as a reviewer of ICML'25.
  • [10/20/24] [Paper] Our paper on dynamic sparse access of KV cache has been accepted to Machine Learning and Compression Workshop NeurIPS'24 ! Thanks to all collaborators!
  • [09/09/24] [Service] Served as a reviewer of ICLR’25.
  • [04/05/24] [Award] I have been selected for the DAC 2024 Young Fellow Program.

Publications

STARC: Selective Token Access with Remapping and Clustering for Efficient LLM Decoding on PIM Systems
Zehao Fan, Yunzhen Liu, Garrett Gagnon, Zhenyu Liu, Yayue Hou, Hadjer Benmeziane, Kaoutar El Maghraoui, Liu Liu
ASPLOSInternational Conference on Architectural Support for Programming Languages and Operating Systems , 2026 | [abs]

SAGE: Saliency-Aware Grouping for Efficient Mapping of LLMs on Analog Compute-in-Memory
Yayue Hou, Zhenyu Liu, Garrett Gagnon, Hsinyu Tsai, Kaoutar El Maghraoui, Geoffrey W. Burr, Liu Liu
ICCADInternational Conference on Computer-Aided Design , 2025 | [abs]

Workshops / Preprints

Bandwidth-Efficient Adaptive Mixture-of-Experts via Low-Rank Compensation
Zhenyu Liu*, Yunzhen Liu*, Zehao Fan, Garrett Gagnon, Yayue Hou, Nan Wu, Yangwook Kang, Liu Liu
arXiv:2512.17073 , 2025 | [abs] | [bib]

Context-Aware Mixture-of-Experts Inference on CXL-Enabled GPU-NDP Systems
Zehao Fan*, Zhenyu Liu*, Yunzhen Liu, Yayue Hou, Hadjer Benmeziane, Kaoutar El Maghraoui, Liu Liu
arXiv:2512.04476 , 2025 | [abs] | [bib]

SINAI: Selective Injection of Noise with Architectural Integration for Robust and Efficient Edge Vision AI
Zhenyu Liu , Yayue Hou, Garrett Gagnon, Sanchari Sen,Swagath Venkatarmani, Nan Wu, Liu Liu
Under ReviewUnder Review , 2025 | [abs]

MAPLE: Memory-Aware Predict and Load for Efficient LLM Inference
Zhenyu Liu , Zhemin Zhang, Zirui Zhang, Yanyuan Qin, Jiayi Luo, Zhenyu Gu, Liu Liu
Compression Workshop @ NeurIPSMachine Learning and Compression Workshop @ NeurIPS 2024 , 2024 | [abs] | [bib]

Enhance DNN Adversarial Robustness and Efficiency via Injecting Noise to Non-Essential Neurons
Zhenyu Liu, Garrett Gagnon, Swagath Venkataramani, Liu Liu
arXiv:2402.04325 , 2024 | [abs] | [bib]

(* indicates equal contribution)

Education

Rensselaer Polytechnic Institute, US
Ph.D. in Electrical, Computer, and Systems Engineering
 Aug. 2023 - Present
University of Electronic Science and Technology of China, China
B.E. in Software Engineering 		Aug. 2019 - Jun. 2023
Overall GPA: 3.93/4.00

Work Experience

Rhymes AI   , Sunnyvale, CA, US
Research Intern, AI Infra Team
Mentor: Zhenyu Gu 		Jul. 2024 - Sept. 2024

Professional Service

Awards &Honors

  • DAC Young Fellows Program 2024 , DAC, 2024
  • National Second Prize, China Computer Design Competition, China, 2021
  • Outstanding Student Scholarship $\times$ 2, UESTC, 2020-2021