U.S. National Science Foundation Expeditions in Computing
Learning Directed Operating System
A Clean-Slate Paradigm for OS Design and Implementation
We are building the next-generation Machine Learning-based Operating System to drive computing infrastructure toward high efficiency and performance.
Recent Publications
Canopy: Property-Driven Learning for Congestion Control
Chenxi Yang, Divyanshu Saxena, Rohit Dwivedula, Kshiteej Mahajan, Swarat Chaudhuri, Aditya Akella
EuroSys, April 2026
Large Language Models as Realistic Microservice Trace Generators
Donghyun Kim, Sriram Ravula, Taemin Ha, Alexandros G. Dimakis, Daehyeok Kim, Aditya Akella
EMNLP, November 2025
Quilt: Resource-Aware Merging of Serverless Workflows
Yuxuan Zhang, Sebastian Angel
SOSP, October 2025
OQueue: Observable Communication in Learning Directed Operating Systems
Aditya Tewari, Sujay Yadalam, Arthur Peters, Saurabh Agarwal, Aditya Akella, Michael Swift, Christopher Rossbach
PACMI, October 2025
Upcoming Events
|
Image
| Undergraduate Research Program Application Deadline October 5, 2025 at 11:59 pm |
|
Image
| LDOS Symposium November 3-4, 2025 |
|
Image
| Directed Reading Program: Software Engineering Skills for LDOS Research Weekly, TBD |
|
Image
| LDOS Undergraduate Reading Program Weekly, TBD |
