Yongkun Du

All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts

Xingsong Ye, Yongkun Du, Jiaxin Zhang +6

Multilingual scene text recognition (STR) remains challenging due to the scarcity of training data for most languages and the difficulty of serving diverse scripts within a single…

HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better

Gengluo Li, Xingyu Wan, Shangpin Peng +20

We present HunyuanOCR-1.5, a lightweight end-to-end OCR-specialized vision-language model. HunyuanOCR unifies document parsing, text spotting, information extraction, text-image tr…

Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods

Xingsong Ye, Yongkun Du, Jiaxin Zhang +5

WordArt (artistic text) features highly customized fonts, textures, and layouts, making WordArt-oriented scene TExt Recognition (WATER) substantially more challenging than general…

ICPR 2026 Competition on Low-Resolution License Plate Recognition

Rayson Laroca, Valfride Nascimento, Donggun Kim +19

Low-Resolution License Plate Recognition (LRLPR) remains a challenging problem in real-world surveillance scenarios, where long capture distances, compression artifacts, and advers…

What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution

Xingsong Ye, Yongkun Du, JiaXin Zhang +3

Large-scale and categorical-balanced text data is essential for training effective Scene Text Recognition (STR) models, which is hard to achieve when collecting real data. Syntheti…

Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting

Hao Feng, Wei Shi, Ke Zhang +9

Document parsing has garnered widespread attention as vision-language models (VLMs) advance OCR capabilities. However, the field remains fragmented across dozens of specialized mod…

Complex Mathematical Expression Recognition: Benchmark, Large-Scale Dataset and Strong Baseline

Weikang Bai, Yongkun Du, Yuchen Su +2

Mathematical Expression Recognition (MER) has made significant progress in recognizing simple expressions, but the robust recognition of complex mathematical expressions with many…

UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters

Yongkun Du, Zhineng Chen, Yazhen Xie +6

Text and formulas constitute the core informational components of many documents. Accurately and efficiently recognizing both is crucial for developing robust and generalizable doc…

MDiff4STR: Mask Diffusion Model for Scene Text Recognition

Yongkun Du, Miaomiao Zhao, Songlin Fan +3

Mask Diffusion Models (MDMs) have recently emerged as a promising alternative to auto-regressive models (ARMs) for vision-language tasks, owing to their flexible balance of efficie…

DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation

Yongkun Du, Pinxuan Chen, Xuye Ying +1

The advent of Multimodal Large Language Models (MLLMs) has unlocked the potential for end-to-end document parsing and translation. However, prevailing benchmarks such as OmniDocBen…

LRANet++: Low-Rank Approximation Network for Accurate and Efficient Text Spotting

Yuchen Su, Zhineng Chen, Yongkun Du +3

End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-t…

Test-Time Reinforcement Learning for GUI Grounding via Region Consistency

Yong Du, Yuchen Yan, Fei Tang +5

Graphical User Interface (GUI) grounding, the task of mapping natural language instructions to precise screen coordinates, is fundamental to autonomous GUI agents. While existing m…

Explicit Relational Reasoning Network for Scene Text Detection

Yuchen Su, Zhineng Chen, Yongkun Du +4

Connected component (CC) is a proper text shape representation that aligns with human reading intuition. However, CC-based text detection methods have recently faced a developmenta…

TextSSR: Diffusion-based Data Synthesis for Scene Text Recognition

Xingsong Ye, Yongkun Du, Yunbo Tao +1

Scene text recognition (STR) suffers from challenges of either less realistic synthetic training data or the difficulty of collecting sufficient high-quality real-world data, limit…

SVTRv2: CTC Beats Encoder-Decoder Models in Scene Text Recognition

Yongkun Du, Zhineng Chen, Hongtao Xie +2

Connectionist temporal classification (CTC)-based scene text recognition (STR) methods, e.g., SVTR, are widely employed in OCR applications, mainly due to their simple architecture…

Decoder Pre-Training with only Text for Scene Text Recognition

Shuai Zhao, Yongkun Du, Zhineng Chen +1

Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. However, the domain gap between synthetic and real ima…

Out of Length Text Recognition with Sub-String Matching

Yongkun Du, Zhineng Chen, Caiyan Jia +2

Scene Text Recognition (STR) methods have demonstrated robust performance in word-level text recognition. However, in real applications the text image is sometimes long due to dete…