PrismAudio / README.md
liuhuadai's picture
Update README.md
4140eb4 verified
|
Raw
History Blame
6.59 kB
metadata
title: PrismAudio
emoji: 🎡
colorFrom: purple
colorTo: blue
sdk: gradio
sdk_version: 5.42.0
python_version: '3.10'
app_file: app.py
pinned: false

PrismAudio

ICLR 2026

arXiv   Online Demo   GitHub   Hugging Face   ModelScope

If you find this project useful,
a star ⭐ on GitHub would be greatly appreciated!


PrismAudio is the first framework to integrate Reinforcement Learning into Video-to-Audio (V2A) generation with specialized Chain-of-Thought (CoT) planning. Building upon ThinkSound's pioneering CoT-based V2A framework, PrismAudio further decomposes monolithic reasoning into four specialized CoT modules (Semantic, Temporal, Aesthetic, and Spatial), each paired with targeted reward functions, enabling multi-dimensional RL optimization that jointly improves reasoning across all perceptual dimensions.


πŸ“° News

  • 2026.03.22   πŸ”₯ We have released PrismAudio, our next-generation video-to-audio generation model! Model weights are available on Hugging Face and ModelScope. For more details, please refer to the prismaudio branch!
  • 2026.01.26 πŸŽ‰ PrismAudio has been accepted to the ICLR 2026 Main Conference!
  • 2025.11.25 πŸ”₯ PrismAudio Online Demo is live!
  • 2025.11.25 πŸ”₯ PrismAudio paper released on arXiv!
  • 2025.09.19 πŸŽ‰ ThinkSound has been accepted to the NeurIPS 2025 Main Conference!
  • 2025.09.01 AudioCoT dataset is now open-sourced on Hugging Face!
  • 2025.07.17 🧠 Finetuning enabled: training and finetuning code is now publicly available!
  • 2025.07.15 πŸ“¦ Simplified installation with Windows .bat scripts for one-click setup!
  • 2025.07.08 πŸ”§ Major update: model lightweighted, optimized memory and GPU usage, supports large-scale high-throughput audio generation!
  • 2025.07.01 Online demo on Hugging Face Spaces and ModelScope!
  • 2025.07.01 Released inference scripts and web interface!
  • 2025.06 ThinkSound paper released on arXiv!
  • 2025.06 Online Demo is live!

⚑ Quick Start

For detailed training and inference code, please refer to ThinkSound (prismaudio branch).


πŸš€ Features

  • V2A SOTA: Achieves state-of-the-art results across all four perceptual dimensions on both VGGSound and AudioCanvas benchmarks.
  • Decomposed CoT Reasoning: Four specialized CoT modules (Semantic, Temporal, Aesthetic, Spatial) each providing focused, interpretable reasoning for its corresponding perceptual dimension.
  • Multi-dimensional RL: Fast-GRPO enables efficient multi-dimensional reward optimization without compromising generation quality.
  • New Benchmark AudioCanvas: A rigorous V2A benchmark with 300 single-event classes and 501 multi-event samples covering diverse and challenging scenarios.
  • Efficient: 518M parameters with faster inference than prior SOTAs.

✨ Method Overview

PrismAudio consists of three main components:

  1. CoT-Aware Audio Foundation Model: Built on a Multimodal Diffusion Transformer with flow matching, enhanced with VideoPrism for video understanding and T5-Gemma for structured CoT text encoding.
  2. Decomposed Multi-Dimensional CoT Reasoning: Four specialized CoT modules β€” Semantic, Temporal, Aesthetic, and Spatial β€” each providing targeted reasoning for its corresponding perceptual dimension.
  3. Fast-GRPO Multi-Dimensional RL Framework: A hybrid ODE-SDE sampling strategy that dramatically reduces training overhead while enabling multi-dimensional reward optimization across all perceptual dimensions.

πŸ“„ License

This project is released under the Apache 2.0 License.

Note: The code, models, and dataset are for research and educational purposes only. Commercial use is NOT permitted. For commercial licensing, please contact the authors.

πŸ“¦ Third-Party Components

  • Stable Audio Open VAE (by Stability AI): Licensed under the Stability AI Community License. Commercial use and redistribution require prior permission from Stability AI.
  • πŸ“˜ All other code and models are released under the Apache License 2.0.

Acknowledgements

Many thanks to:

  • stable-audio-tools (by Stability AI): For providing an easy-to-use framework for audio generation, as well as the VAE module and weights.

πŸ“– Citation

If you find PrismAudio useful in your research or work, please cite our paper:

@misc{liu2025prismaudiodecomposedchainofthoughtsmultidimensional,
    title={PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation}, 
    author={Huadai Liu and Kaicheng Luo and Wen Wang and Qian Chen and Peiwen Sun and Rongjie Huang and Xiangang Li and Jieping Ye and Wei Xue},
    year={2025},
    eprint={2511.18833},
    archivePrefix={arXiv},
    primaryClass={cs.SD},
    url={https://arxiv.org/abs/2511.18833}, 
}

πŸ“¬ Contact ✨ Feel free to open an issue or contact us via email (huadai.liu@connect.ust.hk) if you have any questions or suggestions!