Sina Tayebati
Papers
4
Total Citations
15
H-Index
2
About
Sina Tayebati is an emerging researcher at the forefront of robust autonomous systems, edge computing, and intelligent perception for robotics and autonomous vehicles. His work addresses one of the most pressing challenges in modern autonomy: ensuring that complex sensor arrays — including LiDAR, RADAR, and event cameras — remain reliable and trustworthy under real-world failure conditions. Tayebati's most recognized contribution, STARNet, introduces a novel likelihood regret-based framework for sensor anomaly detection, enabling robust edge autonomy even when hardware behaves unpredictably. Complementing this, his work on masked autoencoder-driven LiDAR perception challenges conventional sensing paradigms by demonstrating that generative pre-training can dramatically reduce the volume of raw sensor data required for accurate 3D environmental understanding. More broadly, his research on the sensing-to-action loop synthesizes these threads into a unified vision for intelligent edge systems capable of real-time decision-making in dynamic environments. With over 15 cumulative citations across publications spanning just two years, Tayebati is rapidly establishing himself as a distinctive voice in resource-efficient, safety-critical autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4