mlsanityData to 7 Oct 2026

WanSong v1.0 Technical Report

arXiv 2607.14749 ↗First posted 16 Jul 2026eess.AS cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fidelity long-form audio while supporting controllability remains challenging. To address these needs, we present WanSong, a simple yet powerful approach for long-form, commercial-grade song generation. Unlike autoregressive (AR) and cascaded multi-stage pipelines (eg, AR followed by diffusion), WanSong is a pure diffusion-based model that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems (vocals and background music) in a single run. In addition, our diffusion framework enables faster inference through step-distillation, and offers an efficient pathway for fine-tuning and customization to support downstream editing tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 19 references that are in the map. First posted on arXiv 16 Jul 2026.

Builds on

19 of 19 references.

References · 19

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  3. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  4. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,010
  5. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  6. 2023MusicLM: Generating Music From Textcited by 442
  7. 2024Seed-TTS: A Family of High-Quality Versatile Speech Generation Modelscited by 293
  8. 2024Stable Audio Opencited by 192
  9. 2025Meta Audiobox Aesthetics: Unified Automatic Quality Assessment for Speech, Music, and Soundcited by 129
  10. 2025YuE: Scaling Open Foundation Models for Long-Form Music Generationcited by 68
  11. 2025MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantizationcited by 66
  12. 2025SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generationcited by 29
7 more
  1. 2025SongEval: A Benchmark Dataset for Song Aesthetics Evaluationcited by 24
  2. 2025LeVo: High-Quality Song Generation with Multi-Preference Alignmentcited by 23
  3. 2026ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generationcited by 22
  4. 2025DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matchingcited by 14
  5. 2025Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generationcited by 13
  6. 2024SongCreator: Lyrics-based Universal Song Generationcited by 12
  7. 2026SongBench: A Fine-Grained Multi-Aspect Benchmark for Song Quality Assessmentcited by 6

Built on by

Not cited yet.