{"slug": "decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs", "title": "Decomposer: Learning to Decompile Symbolic Music (Like MIDI) to Programs", "summary": "Researchers introduced Decomposer, a post-training framework that decompiles symbolic music (MIDI) into editable Strudel programs. Using synthetic data and reinforcement learning, the system outperforms closed-source LLMs in reconstruction faithfulness while generating more readable code.", "body_md": "# Computer Science > Machine Learning\n\n[Submitted on 2 Jul 2026]\n\n# Title:Decomposer: Learning to Decompile Symbolic Music to Programs\n\n[View PDF](/pdf/2607.01849)\n\nAbstract:Musical performance involves executing a set of high-level musical instructions, yet recovering those instructions from the performance is a challenging inverse problem. We present Decomposer, a post-training framework for symbolic music decompilation: the task of recovering executable, editable music programs from symbolic music. We instantiate the task as MIDI-to-Strudel decompilation, where the model takes symbolic MIDI as input and produces a program in Strudel, a music programming language, that reconstructs the input when executed. The task poses two challenges: Strudel is a low-resource language with little naturally paired MIDI-code data, and optimizing faithful reconstruction of MIDI alone can collapse to unreadable note-by-note transliteration. We address these challenges in two stages. First, we construct Strudel-Synth, a synthetic corpus of paired Strudel programs and rendered MIDI, and use it for supervised fine-tuning. Second, we refine the model with reinforcement learning on unpaired MIDI, optimizing rewards for both MIDI reconstruction faithfulness and code readability. Our evaluation across synthetic and real-world MIDI benchmarks shows that Decomposer achieves substantially higher MIDI reconstruction faithfulness than closed-source LLMs while producing more readable and diverse code than the heuristic converter.\n\n### Current browse context:\n\ncs.LG\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\nIArxiv Recommender\n\n*(*[What is IArxiv?](https://iarxiv.org/about))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs", "canonical_source": "https://arxiv.org/abs/2607.01849", "published_at": "2026-07-07 01:57:44+00:00", "updated_at": "2026-07-07 02:30:20.936203+00:00", "lang": "en", "topics": ["machine-learning", "large-language-models", "generative-ai"], "entities": ["Decomposer", "Strudel", "MIDI", "Strudel-Synth"], "alternates": {"html": "https://wpnews.pro/news/decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs", "markdown": "https://wpnews.pro/news/decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs.md", "text": "https://wpnews.pro/news/decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs.txt", "jsonld": "https://wpnews.pro/news/decomposer-learning-to-decompile-symbolic-music-like-midi-to-programs.jsonld"}}