- “Guiding Audio Editing with Audio Language Model” (with Zitong Lan and Mingmin Zhao)
- “Resounding Acoustic Fields with Reciprocity” (with Zitong Lan and Mingmin Zhao)
- “Efficient Uncertainty Quantification in Transformers”
- “Bootstrapping Autonomous Driving Radars with Self-Supervised Learning” (with Sohrab Madani, Junfeng Guan, Mohammed Alloulah, Saurabh Gupta, and Haitham Hassanieh)
- “Rank-DETR for High Quality Object Detection” (with Yifan Pu, Weicong Liang, Yuhui Yuan, Yukang Yang, Chao Zhang, Han Hu, and Gao Huang)
Research Experience
Worked with Prof. Haitham Hassanieh at EPFL, Prof. Saurabh Gupta at UIUC, and Dr. Yuhui Yuan and Dr. Han Hu at Microsoft Research Asia (MSRA).
Education
Ph.D. student in CIS at the University of Pennsylvania, advised by Prof. Mingmin Zhao; Undergraduate at the University of Cambridge, worked in the Machine Learning Group, supervised by Prof. Jose Miguel Hernandez-Lobato.
Background
Research Interests: Multimodal Machine Learning, particularly at the intersection of Computer Vision, Audio Processing, and Sensor Fusion. Excited about applying these techniques to areas such as AR/VR/XR, Immersive Multimedia, Robotics, and Autonomous Driving.