AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

LEGATO: Large-scale End-to-end Generalizable Approach to Typeset OMR

Guang Yang, Victoria Ebert, Nazif Can Tamer, Brian Siyuan Zheng, Luiza Amador Pozzobon, Noah A. Smith

ICLR 2026 · Architectures and efficiency › RNNs and normalization · approach: Learned embeddings for retrieval

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use Legato (frozen pretrained vision encoder + ABC decoder trained on PDMX-Synth) instead of SMT++full-page OMR · Camera OpenScore String QuartetsTEDn: 98.6 -> 62.2Improved
use Legato instead of SMT++ on real IMSLP piano scansfull-page OMR · IMSLP Piano ScoresTEDn: 97.7 -> 29.5Improved
switch SMT++ output from **kern to ABC with BPE tokenizer (ablation)SMT++ on GrandStaff · IMSLP Piano ScoresTEDn: 97.7 -> 74.6Improved
enlarge SMT++ to 177M parameters (ablation)SMT++ on ABC GrandStaff · IMSLP Piano ScoresTEDn: 74.6 -> 73.0No clear effect
train enlarged SMT++ on larger PDMX-Synth data (ablation)SMT++_large · IMSLP Piano ScoresTEDn: 73.0 -> 80.5Hurt
use frozen pretrained vision encoder with Legato architecture and PDMX-Synth instead of SMT++_large (ablation)OMR model · IMSLP Piano ScoresTEDn: 80.5 -> 29.5Improved
use larger decoder (Legato versus Legato_small) (ablation)Legato · IMSLP Piano ScoresTEDn: 75.7 -> 29.5Improved
add three in-context ABC examples to GPT-5 prompt (ablation)GPT-5 · IMSLP Piano ScoresTEDn: 96.7 -> 74.7Improved
prompt GPT-5 for MusicXML instead of ABC (ablation)GPT-5 · IMSLP Piano ScoresTEDn: 96.7 -> 86.6Improved
prompt Gemini 2.5 Pro with in-context ABC examples (ablation)Gemini 2.5 Pro · IMSLP Piano ScoresTEDn: 87.8 -> 78.6Improved
evaluate on violin parts only with Verovio rendering, favoring SMT++Legato versus SMT++ · Rendered String Quartets Violin PartsTEDn: 95.0 -> 7.7Improved
use Legato_small instead of SMT++ on violin partsLegato_small · Rendered String Quartets Violin PartsCER kern: 30.7 -> 50.6Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy