A data-free streaming consistency distillation framework enables single-step autoregressive generation from text-to-music models for real-time interactive use while preserving timbre and rhythm via latent, spectral, and temporal losses.
Music fadernets: Controllable music generation based on high-level features via low-level feature modelling,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.SD 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Activation steering with Gram-Schmidt orthogonalization enables disentangled, deterministic control of pitch and duration attributes in the Multitrack Music Transformer without retraining.
citing papers explorer
-
Real-Time Interactive Music Generation via Data-Free Streaming Consistency Distillation
A data-free streaming consistency distillation framework enables single-step autoregressive generation from text-to-music models for real-time interactive use while preserving timbre and rhythm via latent, spectral, and temporal losses.
-
Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music Generation
Activation steering with Gram-Schmidt orthogonalization enables disentangled, deterministic control of pitch and duration attributes in the Multitrack Music Transformer without retraining.