Real-time Linux
Execution models and system support for predictable, time-critical workloads.
Real-time and embedded systems
Making complex systems predictable
I am Bite (/ˈbiː.tə/) Ye (/jɛ⁵¹/). You can call me Bite, though I don’t bite. I am a PhD student at MPI-SWS advised by Björn B. Brandenburg. I study how Linux systems can deliver reliable performance for time-critical workloads.
About
Research
in real systems
My work sits at the intersection of operating systems, real-time computing, and performance analysis. I am interested in extracting useful models from complex software and using them to make timing behavior easier to understand and control.
Before joining MPI-SWS, I earned my bachelor's and master's degrees from George Washington University, where I worked with Gabriel Parmer. I also worked on platform performance at XPeng.
Research
What I work on
Model inference
Framework-agnostic techniques that recover structure from complex task behavior.
Systems performance
Low-level measurement and analysis across the Linux kernel, eBPF, and embedded platforms.
Tools
What I maintain
LiME
An eBPF-based Linux tool that observes real-time threads and extracts task models from their timing behavior.
LiME Model Extractors
A Rust library of LiME's real-time task-model inference algorithms, with one-shot and streaming extractors.
Publications
What I wrote
2026
IEEE RTAS 2026
Framework-Agnostic Model Inference for Intra-Thread Real-Time Tasks
2025
IEEE RTAS 2025
LiME: The Linux Real-Time Task Model Extractor
2022
IEEE RTSS 2022
Edge-RT: OS Support for Controlled Latency in the Multi-Tenant, Real-Time Edge
2021
IEEE RTAS 2021