Author

Yunhui Deng

h-index 0 View on Semantic Scholar

We have 2 of 2 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Learning to Ground Before Reading: Unified PCB Engineering Drawing Parsing with Compact Vision-Language Models

PCB engineering drawings mix sparse graphics, dense tables, and text whose meaning depends on page position. Localizing the regions and sending crops to specialized recognizers are determined as the methods for most parsers, so missed regions cannot be recovered downstream. We train a compact VLM to read the full page...

Jinghao Liu, Xing-Run Liu, Geng-Chen Sun et al. · 0 citations

Edit, Crop, and Prompt: Training-Free Visual Question Answering via Preprocessing Pipelines for Real-World Visual Illusions

A training-free solution for the 5th Dat-aCV Challenge @ CVPR 2026, Task II: Real-World Visual Illusions and Anomalies, which demonstrates that targeted preprocessing can substantially mitigate the perceptual biases of current vision-language models without any gradient updates.

Jingwei Bao, Yunhui Deng · 0 citations