About me

I am currently a third year Ph.D. student at University of Pennsylvania and work with Mingmin Zhao. Currently I work on multimodal learning, especially focusing on audio/speech/acoustic. I have worked on audio generation, audio language model and acoustic field modeling. Feel free to drop me an email if you are interested in my research for collaborations!

I graduated from Southeast University with a bachelor degree in Electrical Engineering with honor. In the past, I am very fortunate to work with Prof. Tengxiang Zhang, Fusang Zhang, Jie Xiong and Yang Zhang.

Email Google Scholar CV

News

2026-02: Two papers are conditionally accepted by Mobisys’26. (i) AV-Twin introduces a complete framework to capture and reconsutrct an audio-visual digital twin while enbales flexible user edit. (ii) SurfRadar builds a mathmatical connection between high-resolution radar signal and surface properties including permittivity and surface roughness.
2026-01: Here we go! SmartDJ is accepted by ICLR’26!!! See you in Brazil!
2025-11: SmartDJ is accepted by NeurIPS’25 GenProCC workshop with Oral presentation, see you in San Diego!
2025-09: Two papers are accepted at NeurIPS’25 main conference. (i) Versa introduces a learning strategy inspired by the reciprocity principle for acoustic field training. (ii) HoloRadar leverages wall reflections to image the hidden people and object around the corner.
2024-09: Our work on using Acoustic Volume Rendering (AVR) for neural impulse response field is accepted to NeurIPS’24 with Spotlight!
2023-09: I start my PhD journey at Upenn.

Selected Publications

Building Audio-Visual Digital Twins with Smartphones
Zitong Lan, Yiwei Tang, Yuhan Wang, Haowen Lai, Yiduo Hao, Mingmin Zhao
To appear at Mobisys, 2026
[Paper][Demo video]

SmartDJ: Declarative Audio Editing with Audio Language Model
Zitong Lan, Yiduo Hao , Mingmin Zhao
ICLR, 2026
NeurIPS GenProcc, 2025 (Oral)
[Paper] [Project page] [Code]

Surface Characterization with mmWave Signals
Haowen Lai, Zitong Lan, Dongyin Hu, Mingmin Zhao
To appear at Mobisys, 2026

Resounding Acoustic Fields with Reciprocity
Zitong Lan, Yiduo Hao, Mingmin Zhao
NeurIPS, 2025
[Paper][Project page]

Non-Line-of-Sight 3D Reconstruction with Radar
Haowen Lai, Zitong Lan, Mingmin Zhao
NeurIPS, 2025
[Paper][Project page]

Acousitc Volume Rendering for Neural Impulse Response Field
Zitong Lan, Chenhao Zheng, Zhiwei Zheng, Mingmin Zhao
NeurIPS, 2024 (Spotlight)
[Paper][Project page][AVR code][AcoustiX code]

Quantum Wireless Sensing: Principle, Design and Implementation
Fusang Zhang, Beihong Jin, Zitong Lan, Zhaoxin Chang, Daqing Zhang, Yuechun Jiao, Meng Shi, Jie Xiong
Mobicom, 2023
[Paper]

BLEselect: Gestural IoT Device Selection via Bluetooth Angle of Arrival Estimation from Smart Glasses
Tengxiang Zhang, Zitong Lan, Chenren Xu, Yanrong Li, Yiqiang Chen
Ubicomp, 2023
[Paper] [Video]

Exploring quantum sensing for fine-grained liquid recognition
Yuechun Jiao, Jinlian Hu, Zitong Lan, Fusang Zhang, Jie Xiong, Jingxu Bai, Zhaoxin Chang, Yuqi Su, Beihong Jin, Daqing Zhang, Jianming Zhao, Suotang Jia
Arxiv preprint
[Paper]

Experience

Aug. 2023 - Now: Research Assistant, ESE of University of Pennsylvania
Aug. 2022 - May. 2023: Research Assistant, Institute of Software, Chinese Academy of Sciences
Oct. 2022 - Jan. 2023: Research Intern, University of Los Angeles
May. 2021 - Aug. 2022: Research Intern, Institute of Computing Technology, Chinese Academy of Sciences

Awards

2025 NeurIPS top reviewer, CVPR distinguished reviewer.
2024 NeurIPS travel grant.
2023 Howard Broadwell Fellow from Upenn.
2023 Outstanding Graduates in Southeast University. (5%)
2021 University Scholarship in Southeast University. (2%)
2020 IEEE CASS Student Design World Winner. (1st)

Beyond Research…