JAM: A Tiny Flow-based Song Generator with Fine-grained Controllability and Aesthetic Alignment

Documenti analoghi

• Video2Music: Suitable Music Generation from Videos using an Affective Multimodal Transformer model
  di: Kang, Jaeyong, et al.
  Pubblicazione: (2023)
• TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching and Clap-Ranked Preference Optimization
  di: Hung, Chia-Yu, et al.
  Pubblicazione: (2024)
• Leveraging LLM Embeddings for Cross Dataset Label Alignment and Zero Shot Music Emotion Prediction
  di: Liu, Renhang, et al.
  Pubblicazione: (2024)
• JamendoMaxCaps: A Large Scale Music-caption Dataset with Imputed Metadata
  di: Roy, Abhinaba, et al.
  Pubblicazione: (2025)
• NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards
  di: Hung, Chia-Yu, et al.
  Pubblicazione: (2025)