# Making the Most of Limited Data: Score-Aware Training for Text-to-Music Generation

arXiv: https://arxiv.org/abs/2606.07387 · HTML: https://mlsanity.com/paper/2606.07387/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 14 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 12 of 12)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [Stable Audio Open](https://mlsanity.com/paper/2407.14358/) (2024)
- [MuQ: Self-Supervised Music Representation Learning with Mel Residual Vector Quantization](https://mlsanity.com/paper/2501.01108/) (2025)
- [ACE-Step 1.5: Pushing the Boundaries of Open-Source Music Generation](https://mlsanity.com/paper/2602.00744/) (2026)
- [Music Flamingo: Scaling Music Understanding in Audio Language Models](https://mlsanity.com/paper/2511.10289/) (2025)
- [MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows](https://mlsanity.com/paper/2508.06098/) (2025)
- [When Bad Data Leads to Good Models](https://mlsanity.com/paper/2505.04741/) (2025)
- [Academic Text-to-Music Grand Challenge: Datasets, Baselines, and Evaluation Methods](https://mlsanity.com/paper/2605.21538/) (2026)

## Abstract (arXiv)

State-of-the-art text-to-music generation systems rely on massive proprietary datasets and industrial-scale compute, making it impossible to disentangle architectural contributions from resource advantages. We propose textitscore-aware training, which treats audio-caption alignment score as a direct supervision signal throughout the pipeline. Rather than discarding low-scoring segments, we repurpose them via a CLAP-conditioned Beta noise timestep schedule that routes them to high-noise training regimes, acting as an effective implicit regularizer. Complementarily, segment-level filtering removes the most misaligned examples, and a two-stage caption procedure bridges the distribution gap between verbose training captions and concise inference prompts. A REPA auxiliary loss further transfers structured semantic knowledge from pretrained CLAP and MuQ encoders without additional data. Our 450M-parameter FluxAudio-based system, submitted to the ICME 2026 ATTM Grand Challenge Efficiency Track, ranked 2nd across both tracks in the objective evaluation and 3rd in the Efficiency Track in the final MOS evaluation.