Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.
JASCO: Joint audio and symbolic conditioning for temporally controlled text-to-music generation
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
MERIT trains disentangled heads for melody, rhythm, and timbre via conditional audio generation and stem separation, with evaluations showing each head responds strongly to its target dimension and near chance on others across synthetic and real audio.
MindMelody combines real-time EEG emotion decoding with an LLM for intervention planning and a hierarchical controller for generating affect-aware music in a continuous feedback loop.
SketchSong uses temporal sketch planning with high-level tokens and explicit modeling of four tracks (vocals, bass, drums, other) to generate more coherent songs than baselines.
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
-
Auditing Training Data in Generative Music Models via Black-Box Membership Inference
Black-box membership inference on text-to-music models reaches up to 98.6% accuracy by training an auditor on semantic alignment patterns extracted from shadow-model generations.
-
MERIT: Learning Disentangled Music Representations for Audio Similarity
MERIT trains disentangled heads for melody, rhythm, and timbre via conditional audio generation and stem separation, with evaluations showing each head responds strongly to its target dimension and near chance on others across synthetic and real audio.
-
MindMelody: A Closed-Loop EEG-Driven System for Personalized Music Intervention
MindMelody combines real-time EEG emotion decoding with an LLM for intervention planning and a hierarchical controller for generating affect-aware music in a continuous feedback loop.
-
SketchSong: Hierarchical Song Generation with Sketch Planning and Fine-Grained Multi-Track Modeling
SketchSong uses temporal sketch planning with high-level tokens and explicit modeling of four tracks (vocals, bass, drums, other) to generate more coherent songs than baselines.
-
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.