{"ID":5675216,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-07T08:05:00.133216355Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01849","arxiv_id":"2607.01849","title":"Decomposer: Learning to Decompile Symbolic Music to Programs","abstract":"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.","short_abstract":"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 sym...","url_abs":"https://arxiv.org/abs/2607.01849","url_pdf":"https://arxiv.org/pdf/2607.01849v1","authors":"[\"Yewon Kim\",\"Apurva Gandhi\",\"David Chung\",\"Graham Neubig\",\"Chris Donahue\"]","published":"2026-07-02T08:09:52Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.SD\"]","methods":"[\"Reinforcement Learning\",\"Large Language Model\"]","has_code":false}