Posts by Collection

Stealer

You can also find my artist page

CGC opening ceremony in UCSD

Mash-up live: Don’t Ask (cover J.sheon), Maze (cover step.jad), Gorilla (cover Bruno Mars)

Premiere of Movie GG Bond: Interstellar Action

Involved in the production of the theme song - which means you can hear my voice in the movie!

Music Festival

Live: Someone like you (cover Adele)

Enhancing Size Generalization in Graph Neural Networks through Disentangled Representation Learning

Published in International Conference on Machine Learning (ICML), 2024

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

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

Published in The Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

Xuyuan Liu, Yinghao Cai, Qihui Yang, Yujun Yan
Download Paper

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

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

Qihui Yang, Jiahe Lei, Qiuqiang Kong

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

Published in AI Heard That! ICML 2025 Workshop on Machine Learning for Audio, 2025

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

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

Published in Submitted to Top-tier Conference, 2025

Qihui Yang, Randal Leistikow, Yongyi Zang

Learning Interpretable Features in Audio Latent Spaces via Sparse Autoencoders

Published in Mechanistic Interpretability Workshop at NeurIPS 2025, 2025

Nathan Paek, Yongyi Zang, Qihui Yang, Randal Leistikow

Multimodal Room Impulse Response Generation Through Latent Rectified Flow Matching

Published in Submitted to Top-tier Conference, 2025

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

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

Published in 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

A Unified Perspective From Statistical Inference to Generative Modeling

Published: January 20, 2025

Focusing on the application of probabilistic and statistical principles to generative modeling, this sharing explores the connections between different generative models in a statistical learning framework, including score-based and flow-based generative models, in a step-by-step manner. Sharing will start with basic concepts to ensure the audience understands the required math, providing intuitive explanations as they progress into key theories. Finally, based on an in-depth analysis of existing work on generative modeling, the sharing suggests guidelines that can help with theoretical machine learning research, aiming to provide practical implications for participants.