|
Juyang Bai I am a fourth year Ph.D. student in JHU ECE. I am fortunate to be advised by Prof. Laixi Shi. My research focuses on algorithm–system co-design for efficient and trustworthy machine learning systems. Specifically, I work toward making post-training, inference, and real-world deployment of foundation models both efficient and trustworthy (robust, safe, and secure). My current work centers on reinforcement learning for agentic AI, in particular multi-agent LLM systems, and extends to physical AI, from robots to edge devices. |
News
|
Research |
|
MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?
Juyang Bai, Laixi Shi arXiv, 2026 [Website] [Paper] [Code] |
|
Phantom: Privacy-Preserving Deep Neural Network Model Obfuscation in Heterogeneous TEE and GPU System
Juyang Bai, Md Hafizul Islam Chowdhuryy, Jingtao Li, Yao Fan, Chaitali Chakrabarti, Deliang Fan USENIX Security, 2025 [Website] [Paper] [Code] |
|
Learning Representation for Anomaly Detection of Vehicle Trajectories
Ruochen Jiao, Juyang Bai, Xiangguo Liu, Takami Sato, Xiaowei Yuan, Qi Alfred Chen, Qi Zhu IROS, 2023 [Website] [Paper] |
|
Towards a Toolkit for Free Living Wearable Development
Blaine Rothrock, Alexander Curtiss, Juyang Bai, Josiah Hester UbiComp/ISWC, 2022 [Website] [Paper] |
|
Template from Jon Barron. Thanks Jon! |