Publications

WildFX: A DAW-Powered Pipeline for In-the-Wild Audio FX Graph Modeling

Oral Paper 29th International Conference on Digital Audio Effects (DAFx-26) · 2026 · MIT, Cambridge, MA, USA

Qihui Yang, Taylor Berg-Kirkpatrick, Julian McAuley, Zachary Novack.

Paper Preprint Code Program

FlowSynth: Instrument Generation Through Distributional Flow Matching and Test-Time Search

Poster IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026) · 2026 · Barcelona, Spain

Qihui Yang, Randal Leistikow, Yongyi Zang.

Paper Program

StylePitcher: Generating Style-Following, Expressive Pitch Curves for Versatile Singing Tasks

Best Paper @ NeurIPS 2025 Workshop on AI for Music: Where Creativity Meets Computation · 2025

Jingyue Huang, Qihui Yang, Fei-Yueh Chen, Randal Leistikow, Yongyi Zang

Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders

Mechanistic Interpretability Workshop at NeurIPS 2025 · 2025

Nathan Paek, Yongyi Zang, Qihui Yang, Randal Leistikow

One-shot Text-aligned Virtual Instrument Generation Utilizing Diffusion Transformer

Audio Imagination: NeurIPS 2024 Workshop on AI-Driven Speech, Music, and Sound Generation · 2024

Qihui Yang, Jiahe Lei, Qiuqiang Kong

Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks

The Annual Conference on Neural Information Processing Systems (NeurIPS) · 2024

Xuyuan Liu, Yinghao Cai, Qihui Yang, Yujun Yan

Paper

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning

International Conference on Machine Learning (ICML) · 2024

Zheng Huang, Qihui Yang, Dawei Zhou, Yujun Yan.

Paper

Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching

Preprint · 2025

Ali Vosoughi*, Yongyi Zang*, Qihui Yang, Nathan Paek, Randal Leistikow, Chenliang Xu