← Search

Brian Siyuan Zheng

2 accepted papers

2026

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

ICLR 2026poster

We propose Legato, a new end-to-end model for optical music recognition (OMR), a task of converting music score images to machine-readable documents. Legato is the first large-scale pretrained OMR model capable of recognizing full-page or multi-page typeset music scores and the first to generate do…

Cited by 0SourcecodeScholar
2025

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations

NeurIPS 2025spotlight

Modern tokenizers employ deterministic algorithms to map text into a single ``canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the language model vocabulary, including tokenizing by character. In this paper, we investigate the robustness of LMs…

Cited by 0SourceScholar