Scholar
Cheng-Zhi Anna Huang
Google Scholar ID: NRz_EVgAAAAJ
MIT Music and Theater Arts (MTA) and Electrical Engineering and Computer Science (EECS)
Citations & Impact
Citations
3,002
H-index
13
i10-index
14
Publications
20
Co-authors
19
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Created Coconet, which powered Google’s first AI Doodle, the Bach Doodle, harmonizing 55 million melodies from users around the world in two days. In 2018, created Music Transformer, a breakthrough in generating music with long-term structure, and the first successful adaptation of the transformer architecture to music. The ICLR paper is currently the most cited paper in music generation.
Research Experience
- For the past 8 years, worked as a researcher at Magenta in Google Brain and then Google DeepMind, focusing on developing AI models and interfaces to support music creation. Held a Canada CIFAR AI Chair at Mila and an adjunct professorship at the University of Montreal. Was a judge and organizer for the AI Song Contest from 2020-2022.
Education
- PhD: Harvard University; Master's: MIT Media Lab; Dual Bachelor's: University of Southern California, majoring in Music Composition and Computer Science.
Background
- Research Interests: Generative AI, music interaction, human-AI collaboration, music theories and cognition. Professional Fields: Electrical Engineering and Computer Science, Music and Theater Arts. Brief Introduction: Started a faculty position at Massachusetts Institute of Technology (MIT) in Fall 2024, with a shared position between Electrical Engineering and Computer Science (EECS) and Music and Theater Arts (MTA).
Miscellany
- Personal Interests: Working with musicians to design interactive systems and visualizations that empower them to understand, debug, steer, and align the generative AI’s behavior. Also interested in rethinking generative AI through the lens of social reinforcement learning and multi-agent RL, to elicit creativity through interaction rather than imitation.
