MR-FlowDPO: Multi-Reward Direct Preference Optimization for Flow-Matching Text-to-Music Generation

Documenti analoghi

• MusicFlow: Cascaded Flow Matching for Text Guided Music Generation
  di: Prajwal, K R, et al.
  Pubblicazione: (2024)
• Generative Pre-training for Speech with Flow Matching
  di: Liu, Alexander H., et al.
  Pubblicazione: (2023)
• Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation
  di: Tal, Or, et al.
  Pubblicazione: (2024)
• Audiobox TTA-RAG: Improving Zero-Shot and Few-Shot Text-To-Audio with Retrieval-Augmented Generation
  di: Yang, Mu, et al.
  Pubblicazione: (2024)
• Auto-Regressive vs Flow-Matching: a Comparative Study of Modeling Paradigms for Text-to-Music Generation
  di: Tal, Or, et al.
  Pubblicazione: (2025)