Quanling Zhao | University of California San Diego

About Me

I am a Ph.D. student in Computer Science at the University of California San Diego, advised by Prof. Tajana Rosing. My research develops efficient and theoretically grounded machine learning methods, with interests spanning randomized and kernel methods, efficient LLM/VLM inference, and vector-symbolic / hyperdimensional computing. I am particularly interested in methods that combine principled representations with practical efficiency and systems impact.

Research Interests

Efficient machine learning: efficient inference, representation learning, and statistical learning.
LLM/VLM efficiency: KV-cache reuse, quantization, and efficient inference for long-context and agentic systems.
Randomized and kernel methods: scalable density estimation, random features, and kernel approximation.
Vector-symbolic / hyperdimensional computing: efficient representations, learning, memory, and systems co-design.

News

[2026] AgentKVShift accepted to NeurIPS 2026.
[2026] HDDB appeared at DAC 2026.
[2025] NysHD appeared at AAAI 2025.

Publications

Manuscripts Under Review

Superposed Latent Autoencoder

Quanling Zhao, Jiaying Yang, Tianqi Zhang, Ziyang Hao, Fatemeh Asgarinejad, Flavio Ponzina, Tajana Rosing

Submitted to ICLR 2027.

arXiv

RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection

Quanling Zhao, Jiaying Yang, Ye Tian, Josh Victoria, Zhijun Wang, Pietro Mercati, Onat Gungor, Tajana Rosing

Submitted to ICLR 2027.

arXiv

Superposed Inference for Hyperdimensional Computing

Quanling Zhao, Nilesh Prasad Pandey, Ye Tian, Tajana Rosing

Submitted to ICLR 2027.

Peer-Reviewed Publications

AgentKVShift: Efficient KV Cache Reuse for Agentic Memory Systems NeurIPS

Nilesh Prasad Pandey, Jason Kong, Lanxiang Hu, Quanling Zhao, Yujie Zhao, Onat Gungor, Hao Zhang, Tajana Rosing

Conference on Neural Information Processing Systems (NeurIPS), 2026.

arXiv

HDDB: Efficient In-Storage SQL Database Search Using Hyperdimensional Computing on Ferroelectric NAND Flash DAC

Quanling Zhao*, Yanru Chen*, Runyang Tian, Sumukh Pinge, Weihong Xu, Augusto Vega, Steven Holmes, Saransh Gupta, Tajana Rosing

Design Automation Conference (DAC), 2026.

arXiv * Equal contribution

Online Open-World Wafer Defect Discovery using Hyperdimensional Computing ASP-DAC

Quanling Zhao, Ava Emami, Tsuyoshi Ide, Rajiv Joshi, Steve Holmes, Michael Passow, Tajana Rosing

Asia and South Pacific Design Automation Conference (ASP-DAC), 2027.

FeUHD: Unsupervised Federated Learning using Hyperdimensional Computing TCASAI

You Hak Lee, Keming Fan, Xiaofan Yu, Quanling Zhao, Flavio Ponzina, Tajana Rosing

IEEE Transactions on Circuits and Systems for Artificial Intelligence (TCASAI), 2026.

Paper arXiv

Bridging the Gap between Hyperdimensional Computing and Kernel Methods via the Nyström Method AAAI

Quanling Zhao, Anthony Thomas, Ari Brin, Xiaofan Yu, Tajana Rosing

AAAI Conference on Artificial Intelligence (AAAI), 2025.

Paper arXiv Code

Offload Rethinking by Cloud Assistance for Efficient Environmental Sound Recognition on LPWANs SenSys

Le Zhang*, Quanling Zhao*, Run Wang, Shirley Bian, Onat Gungor, Flavio Ponzina, Tajana Rosing

ACM Conference on Embedded Networked Sensor Systems (SenSys), 2025.

Paper arXiv * Equal contribution

MultimodalHD: Federated Learning Over Heterogeneous Sensor Modalities using Hyperdimensional Computing DATE

Quanling Zhao, Xiaofan Yu, Shengfan Hu, Tajana Rosing

Design, Automation, and Test in Europe (DATE), 2024.

Paper Code

Async-HFL: Efficient and Robust Asynchronous Federated Learning in Hierarchical IoT Networks IoTDI

Xiaofan Yu, Ludmila Cherkasova, Harsh Vardhan, Quanling Zhao, Emily Ekaireb, Xiyuan Zhang, Arya Mazumdar, Tajana Rosing

ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI), 2023.

Paper arXiv

Invited Talks

Connecting Kernel Methods and Hyperdimensional Computing for Capable and Efficient Learning
CoCoSys Center Seminar — July 2026 [Slides]
Towards Generalized Learning in Hyperdimensional Computing: Density Estimation and Hybrid Models
CoCoSys Center Seminar — July 2025 [Slides]

Service

Program Committee: AAAI 2026, AAAI 2027

Conference Reviewer: ICLR 2027, NeurIPS 2026, ICML 2026, RAAAI@NeurIPS 2026, IJCNN 2025, MLNCP@NeurIPS 2024

Journal Reviewer: IEEE/ACM Transactions on Networking, IEEE Access, IEEE Transactions on Cognitive Communications and Networking, IEEE Transactions on Emerging Topics in Computing, IEEE Transactions on Neural Networks and Learning Systems, IEEE Journal of Biomedical and Health Informatics