52 citations · 333 across the 67 of their papers we have counts for
10 papers · 1 filter
AutoSynth: Learning to Generate Editable Synthesizer Programs from Audio and Text
Tristan Wu, Daniel Chin, Liwei Lin +2
Audio generation models can translate natural-language descriptions into sound, but their outputs are typically waveforms. Their audio quality is constrained by audio compression,…
SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision
Junyan Jiang, Ruibin Yuan, Jiahao Pan +4
Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarc…
From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment
Liwei Lin, Gus Xia
How can we understand what a music foundation model has learned \textit{internally}? Most interpretability approaches, such as probing and Sparse Autoencoders (SAEs), focus on iden…
YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality
Ruibin Yuan, Jiahao Pan, Junyan Jiang +32
Symbolic models make melody, harmony, rhythm, and form explicit but typically stop before a finished recording; audio models produce complete songs while leaving composition implic…
Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping
Jingwei Zhao, Gus Xia, Ziyu Wang +1
What is music style? Though often described using text labels such as "swing," "classical," or "emotional," the real style remains implicit and hidden in concrete music examples. I…
Calliphony: A Calligraphy-Driven Interface for Real-Time Generative Music Performance
Tristan Wu, Ruiji Yu, Gus Xia
While music generative models have recently gained significant attention, how they can be effectively integrated into live music performances still requires further exploration. Th…
DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement Learning
Tristan Wu, Daniel Chin, Junan Zhang +3
Synthesizer inversion is challenging for two main reasons: 1) Distinct parameter configurations can produce perceptually similar sounds. 2) Parameter-space losses often fail to ref…
Turning music identification into a neural forward pass
Muhammad Taimoor Haseeb, Ahmad Hammoudeh, Gus Xia
Search, a foundational operation in computer science, maps a query to a matching item in a collection. It is typically implemented as a System-2 like, rule-based pipeline in which…
RenCon 2025: Revival of the Expressive Performance Rendering Competition
Huan Zhang, Taegyun Kwon, Anders Friberg +7
This paper presents a comprehensive documentation of RenCon 2025, the revival of the expressive performance rendering competition which took place at ISMIR 2025 in Daejeon, Korea.…
ViTex: Visual Texture Control for Multi-Track Symbolic Music Generation via Discrete Diffusion Models
Xiaoyu Yi, Qi He, Gus Xia +1
In automatic music generation, a central challenge is to design controls that enable meaningful human-machine interaction. Existing systems often rely on extrinsic inputs such as t…