I'm a researcher in Efficient Machine Learning, focusing on lightweight models, data-efficient learning, and on-device AI. My work aims to make machine learning more practical and accessible for real-world applications.
Images and text inherently exhibit hierarchical structures, e.g. scenes built from objects, sentences built from words. In many computer vision and natural language processing tasks, learning accurate prediction models requires analyzing the correlation of the local primitives of both the input and output data. In this thesis, we develop techniques for learning local representations of images and text and demonstrate their effectiveness on visual recognition, retrieval, and synthesis. ...