I am a PhD candidate at University of California, San Diego. My interests broadly lie in computer vision, machine learning and robotics. I am particularly passionate about understanding the intrinsic complexity of the underlying information acquisition and utilization problems in these domains. Towards this goal, I propose novel algorithms and analyze their behaviors on real-world datasets as well as theoretical models. I worked on improving detection and automated multi-task network design. In both cases my vantage point was to structure the parameters and computations of the model in an adaptive manner, so as to make the resultant solution is more efficient and effective. My adviser is Professor Tara Javidi.