About
I am an Associate Professor of Computer Science and Engineering at the University of Texas at Arlington (UTA). Before joining UTA, I was an Assistant Professor at the State University of New York (SUNY) at Binghamton. I received my Ph.D. from Purdue University, where I conducted research in the FRIENDS Lab under the direction of Professor Dongyan Xu. I am the recipient of an NSF CAREER Award (2023).
My research focuses on making cloud and AI infrastructure faster, safer, and more efficient. I am particularly interested in practical tensions that arise in real systems: how to isolate workloads without giving up performance, how to move data across memory tiers and hosts without disrupting applications, and how to make better use of increasingly heterogeneous hardware. These questions have shaped my work on lightweight secure containers and virtualization, transparent memory tiering across DRAM, CXL, and accelerators, high-throughput networking and storage for cloud workloads, and systems support for large-scale LLM training and inference. Much of this work is motivated by real deployment needs and carried out in collaboration with industry partners.
Selected/recent Publications
View full list- NeurIPS 2026SPIRIT: Speed-Driven Online Adaptation for Self-Speculative Decodingto appear
- ATC 2026Courier: Host-Transparent Direct Network I/O for Secure Containers in Cloud VMsto appear
- SC 2026Quantifying the Cost of Software-Managed Synchronization on Multi-Host CXL Memoryto appear
- OSDI 2026vBOIDs: Taming Chaos via Coarse-grained Scheduling Abstraction for Containers
- OSDI 2026JANUS: Cross-World, Cooperative Nested Virtualization for Secure Containers
- HPDC 2026Scaling Attention Beyond GPUs for LLM Inference
- EuroSys 2026AEP: Achieving Hierarchical Fault Tolerance in DSM Through Atomic Execution Protection
- ATC 2025LiteShield: Secure Containers via Lightweight, Composable Userspace μKernel Services
- ATC 2025DSA-2LM: A CPU-Free Tiered Memory Architecture with Intel DSA
- VLDB 2025mLoRA: Fine-Tuning LoRA Adapters via Highly-Efficient Pipeline Parallelism in Multiple GPUs
- VLDB 2024DLRover-RM: Resource Optimization for Deep Recommendation Models Training in Cloud
- OSDI 2024Nomad: Non-exclusive Memory Tiering via Transactional Page Migration
- SOSP 2023PVM: Efficient Shadow Paging for Deploying Secure Containers in Cloud-native Environment
- ATC 2023p2Cache: Exploring Tiered Memory for In-Kernel File Systems Caching
- EuroSys 2021Parallelizing Packet Processing in Container Overlay Networks
- EuroSys 2020PLASMA: Programmable Elasticity for Stateful Cloud Computing Applications
Sponsored Projects
National Science Foundation
- User-transparent Data Management for Persistence and Crash-consistency in Non-volatile MemoriesNSF2023 – 2027
- Rethinking Virtualization in Cloud-Native SystemsNSF2023 – 2028
- Salvaging Commodity Operating Systems to Support Emerging Networking TechnologiesNSF2019 – 2023
Air Force Research Laboratory
- Enabling Lightweight, Assured Secure Containers for Container-based Orchestration PlatformsAFRL2025 – 2028
- Enabling Lightweight Secure Containers with Assured IsolationAFRL2024 – 2025
Teaching
Students
Current Ph.D. Students
- Yan Wang
- Yang Song
- Chenfei Liao
- Chengbo Zhan
Alumni
- Yu Sun