Mason L. Wang

I am an EECS PhD student at MIT CSAIL, where I am working with Professor Anna Huang. I am interested in audio, generative modeling, and signal processing.

I received my master's in Electrical Engineering at Stanford University working at the Stanford Vision and Learning Lab. I was advised by Jiajun Wu and Mert Pilanci.

You can contact me at masonlwang32 [at] gmail [dot] com. Or, you can find me on Twitter, LinkedIn.

Publications
	Hearing Anything Anywhere Mason L. Wang, Ryosuke Sawata, Samuel Clarke, Ruohan Gao, Elliott Wu, Jiajun Wu CVPR, 2024 video / paper / website / dataset / code / arkiv We create a method of capturing real acoustic spaces from 12 RIR measurements, letting us play any audio signal in the room and listen from any location/orientation. We develop an 'audio inverse-rendering framework' that allows us to synthesize the room's acoustics (monoaural and binaural RIRs) at novel locations and create immersive auditory experiences (simulating music).
	SoundCam: A Dataset for Finding Humans Using Room Acoustics Mason L. Wang, Samuel Clarke, Jui-Hsien Wang, Ruohan Gao, Jiajun Wu NeurIPS Datasets and Bencmharks, 2023 project page / video / arXiv Humans induce subtle changes to the room's acoustic properties. We can observe these changes (explicitly via RIR measurement, or by playing and recording music in the room) and determine a person's location, presence, and identity.
	RealImpact: A Dataset of Impact Sound Fields for Real Objects Samuel Clarke, Ruohan Gao, Mason L. Wang, Mark Rau, Julia Xu, Jui-Hsien Wang, Doug James, Jiajun Wu CVPR, 2023 (Highlight, Top 2.5% of Submissions) project page / video / arXiv Everyday objects possess distinct sonic characteristics determined by their shape and material. RealImpact is the largest dataset of object impact sounds to date, with 150,000 recordings of impact sounds from 50 objects of varying shape and material.
	Subtractive Training for Music Stem Insertion Using Latent Diffusion Models Ivan Villa-Renteria, Mason L. Wang, Zachary Shah, Zhe Li, Soohyun Kim, Neelesh Ramachandran, Mert Pilanci ICASSP*, 2025 paper / examples We use a dataset of full-mix songs, stem-subtracted songs, and LLM-generated edit instructions to train a stem editing/insertion diffusion model.

Education and Experience
	MIT August 2024-? EECS PhD Student Cambridge, Massachusetts
	SONY AI June 2024-August 2024 Research Intern, Music Foundation Model Team Tokyo, Japan
	Stanford University September 2022-June 2024 M.S. in Electrical Engineering, specialization in Signal Processing and Optimization GPA: 4.22/4.3 Course Assistant for ENGR 108 (3x), EE 178 (1x) Research Assistant in CS (1x), EE (1x)
	The University of Chicago October 2018-June 2022 B.S. in Computer Science with a Specialization in Machine Learning B.A. in Mathematics GPA: 4.0/4.0 Honors: Odyssey Scholar, Enrico Fermi Scholar, Robert Maynard Hutchins Scholar, Summa Cum Laude