Published several papers including 'The Sound of Simulation: Learning Multimodal Sim-to-Real Robot Policies with Generative Audio' (CoRL 2025, Best Paper Finalist), 'Sounding that Object: Interactive Object-Aware Image to Audio Generation' (ICML 2025), 'Audio Texture Manipulation by Exemplar-Based Analogy' (ICASSP 2025). Received Sony Research Award.
Research Experience
Part of Berkeley Artificial Intelligence Research (BAIR) Lab, involved in multiple projects such as learning multimodal sim-to-real robot policies and interactive object-aware image to audio generation.
Education
UC Berkeley, Ph.D. in Computer Science, Advisor: Gopala Anumanchipalli; IIIS, Tsinghua University, Collaborated with Hang Zhao; Duke University, Collaborated with Ming Li.
Background
Currently a fourth-year CS Ph.D. student at UC Berkeley, exploring how we acquire physical common sense by leveraging sound, a neglected source of physical truth, to understand the substance of objects beyond what vision reveals. Advised by Gopala Anumanchipalli and collaborated with Andrew Owens. Previously worked with Hang Zhao from IIIS, Tsinghua University, and Ming Li from Duke University.