Author

Lianwen Jin

Observed name: Jin, Lianwen

Institution: South China University of Technology

Observed institution: South China University of Technology

OpenAlex ID: A5126835491

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

2026 · Ye, Xingsong, Du, Yongkun, et al. · arXiv (Cornell University) · 2

DocIntent: Answerability-Guided Agentic Restoration for Real-World Document Visual Question Answering

2026 · Huang, Zihan, Wu, Shihang, et al. · arXiv (Cornell University)

One Patch Is Enough: Reinforcement-Optimized Visual Token Grounding for MLLM-Based Scene Text Spotting

2026 · Tang, Rui, Yang, Wentao, et al. · arXiv (Cornell University)

Works count: 3

Citation count: 2

H-index: 1

I10-index: