I'm a final year Ph.D. candidate in Computer Science and Engineering at the University at Buffalo, where I design and build robust systems for real-time cyber-physical applications. My Ph.D. research focuses on the "systems" dimension of Visual SLAM -- specifically, how system design can drive the performance and reliability of Visual SLAM in real-world environments.
My work sits at the intersection of systems research and applied engineering. I have extensive experience with a wide range of technical stacks and robotics/vision libraries, including Rust, C++, Python, ROS, OpenCV, GTSAM, g2o, and Foxglove. A core theme of my research is introducing Rust into the robotics space. Most recently, I led the development of Bauhaus, a Rust-based framework for modular, memory-safe Visual SLAM systems.
Outside academia, I’ve contributed to production-scale systems at Google and edX -- from building predictive models to reduce Chromium page latency, to improving video infrastructure and engagement features in large-scale learning platforms.
Publications
-
(In submission) Sofiya Semenova, Nitin Vinod, Steven Y. Ko, Yu David Liu, Lukasz Ziarek, and Karthik Dantu. "Bauhaus: A Modular, Memory-Safe Framework for Next-Generation Visual SLAM Systems."
-
Sofiya Semenova, Steven Y. Ko, Yu David Liu, Lukasz Ziarek, and Karthik Dantu. "A Comprehensive Study of Systems Challenges in Visual Simultaneous Localization and Mapping Systems." ACM Transactions on Embedded Computing Systems (TECS). 2024.
-
Sofiya Semenova, Steven Y. Ko, Yu David Liu, Lukasz Ziarek, and Karthik Dantu. "A Quantitative Analysis of System
Bottlenecks in Visual SLAM." ACM International Workshop on Mobile Computing Systems and Applications (HotMobile). 2022. Best Poster Award
-
Sofiya Semenova, Pranay Meshram, Timothy Chase, Steven Y. Ko, Yu David Liu, Lukasz Ziarek, and Karthik Dantu.
"A Modular, Extensible Framework for
Modern Visual SLAM Systems. (Poster)” International Conference on Mobile Systems, Applications and Services
(MobiSys). 2022.
-
Ali J. Ben Ali, Sofiya Semenova and Marziye Kouroshli, Zakieh Sadat Hashemifar, Steven Y. Ko, and Karthik Dantu. "Edge-SLAM: Edge-Assisted Visual Simultaneous Localization and Mapping." ACM Transactions on Embedded Computing Systems (TECS). 2022.
-
Ali J. Ben Ali, Sofiya Semenova, and Karthik Dantu. "Platform Variability in Edge-Cloud Vision Systems. (Poster)" ACM International Workshop on Mobile Computing Systems and Applications (HotMobile). 2019.
-
Ryan Marcus, Olga Papaemmanouil, Sofiya Semenova, and Solomon Garber. "NashDB: An Economic Approach to Fragmentation, Replication and Provisioning for Elastic Databases." ACM Special Interest Group in Data Management (SIGMOD). 2018.
-
Ryan Marcus, Sofiya Semenova, and Olga Papaemmanouil. "A Learning-based Service for Cost and Performance Management of Cloud Databases (Demonstration)." IEEE International Conference on Data Engineering (ICDE). 2017.
Projects
-
For older projects, see the projects page of this website.
My Erdos number is 5, and my Kristen Stewart number is 6.