Kamilya Smagulova

King Abdullah University of Science and Technology

Papers

Total Citations

H-Index

About

Kamilya Smagulova is a rising researcher at the forefront of neuromorphic vision and efficient deep learning, with a focus on event-based object detection for autonomous systems. Her most-cited work introduces a recurrent YOLOv8-based framework that addresses fundamental limitations of conventional frame-based RGB sensors—namely motion blur and poor performance under extreme lighting conditions. By integrating recurrent neural architectures with the YOLOv8 detection pipeline, Smagulova’s approach enables robust, real-time perception from event cameras, which asynchronously capture brightness changes rather than full frames. This innovation is critical for applications in autonomous vehicles and advanced robotics, where speed and reliability under dynamic lighting are paramount. With 15 citations already for this 2025 publication, her work is rapidly gaining recognition for bridging the gap between event-based sensing and state-of-the-art object detection. Smagulova’s contributions are helping to define a new paradigm in vision systems, moving beyond the constraints of traditional cameras toward more resilient, biologically inspired sensing. Her research promises to accelerate the deployment of safer, more capable autonomous agents in real-world environments.