MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
Audio prompt adapter: Un- leashing music editing abilities for text-to-music with lightweight finetuning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
UAT presents a diffusion-centric framework coupling continuous latent diffusion for audio with masked discrete diffusion for text in a shared dual-stream backbone to enable unified generation, editing, and captioning.
AnchorSteer couples self-discovered semantic concept vectors with structural anchoring in diffusion models to achieve controllable music editing with preserved structure.
The work formalizes zero-shot symbolic drum editing as LLM reasoning over a drumroll grid notation, evaluates it on a new benchmark with automated symbolic unit tests, and reports up to 68% success across eight models.
citing papers explorer
-
MIDI-Informed Singing Accompaniment Generation in a Compositional Song Pipeline
MIDI-SAG generates consistent long-form singing accompaniments by feeding symbolic MIDI timing, chords, and structure labels into a compositional pipeline built from pre-trained modules.
-
UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning
UAT presents a diffusion-centric framework coupling continuous latent diffusion for audio with masked discrete diffusion for text in a shared dual-stream backbone to enable unified generation, editing, and captioning.
-
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
AnchorSteer couples self-discovered semantic concept vectors with structural anchoring in diffusion models to achieve controllable music editing with preserved structure.
-
Not that Groove: Zero-Shot Symbolic Music Editing
The work formalizes zero-shot symbolic drum editing as LLM reasoning over a drumroll grid notation, evaluates it on a new benchmark with automated symbolic unit tests, and reports up to 68% success across eight models.