# Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors

arXiv: https://arxiv.org/abs/2601.05508 · HTML: https://mlsanity.com/paper/2601.05508/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 55 references that are in the map.
- First posted on arXiv 9 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [A Neural Representation of Sketch Drawings](https://mlsanity.com/paper/1704.03477/) (2017)
- [DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients](https://mlsanity.com/paper/2212.07766/) (2022)
- [Language Modelling with Pixels](https://mlsanity.com/paper/2207.06991/) (2022)
- [Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing](https://mlsanity.com/paper/2412.19806/) (2024)
- [CoSE: Compositional Stroke Embeddings](https://mlsanity.com/paper/2006.09930/) (2020)
- [ELSED: Enhanced Line SEgment Drawing](https://mlsanity.com/paper/2108.03144/) (2021)
- [Deciphering Oracle Bone Language with Diffusion Models](https://mlsanity.com/paper/2406.00684/) (2024)
- [Multilingual Pretraining for Pixel Language Models](https://mlsanity.com/paper/2505.21265/) (2025)
- [The Impact of Visual Information in Chinese Characters: Evaluating Large Models' Ability to Recognize and Utilize Radicals](https://mlsanity.com/paper/2410.09013/) (2024)
- [Ancient-Modern Chinese Translation with a Large Training Dataset](https://mlsanity.com/paper/1808.03738/) (2018)
- [Hierarchical Character Embeddings: Learning Phonological and Semantic Representations in Languages of Logographic Origin using Recursive Neural Networks](https://mlsanity.com/paper/1912.09913/) (2019)
- [Breaking the Representation Bottleneck of Chinese Characters: Neural Machine Translation with Stroke Sequence Modeling](https://mlsanity.com/paper/2211.12781/) (2022)
- [Finding structure in logographic writing with library learning](https://mlsanity.com/paper/2405.06906/) (2024)
- [DongbaMIE: A Multimodal Information Extraction Dataset for Evaluating Semantic Understanding of Dongba Pictograms](https://mlsanity.com/paper/2503.03644/) (2025)
- [StrokeNet: Unveiling How to Learn Fine-Grained Interactions in Online Handwritten Stroke Classification](https://mlsanity.com/paper/2512.06290/) (2025)

## Abstract (arXiv)

Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet, current advanced Large Language Models (LLMs) and Multimodal LLMs (MLLMs) usually remain structurally blind to this information. LLMs process characters as textual tokens, while MLLMs additionally view them as raw pixel grids. Both fall short to model the underlying logic of character strokes. Furthermore, existing structural analysis methods are often script-specific and labor-intensive. In this paper, we propose Hieroglyphic Stroke Analyzer (HieroSA), a novel and generalizable framework that enables MLLMs to automatically derive stroke-level structures from character bitmaps without handcrafted data. It transforms modern logographic and ancient hieroglyphs character images into explicit, interpretable line-segment representations in a normalized coordinate space, allowing for cross-lingual generalization. Extensive experiments demonstrate that HieroSA effectively captures character-internal structures and semantics, bypassing the need for language-specific priors. Experimental results highlight the potential of our work as a graphematics analysis tool for a deeper understanding of hieroglyphic scripts. View our code at https://github.com/THUNLP-MT/HieroSA.