Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation
Yuheng Chen, Yufan Chen, Zhuojun Cai, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Weijia Fan, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen
Yufan Chen
Ph.D. Student and Research Assistant
I advance structured document intelligence at the intersection of vision, language, and geometry, developing systems that reconstruct latent page structure, reason over complex document relations, ground multimodal answers in verifiable visual evidence, and remain reliable under real-world distribution shifts.
During my Ph.D., I am supervised by Prof. Rainer Stiefelhagen at KIT, with close mentorship from Prof. Jiaming Zhang. During my research visit to Oxford VGG, I am supervised by Prof. Andrew Zisserman.
Education
- Karlsruhe Institute of Technology Ph.D. Student in Computer Vision and Document Analysis
- University of Stuttgart M.Sc. Electrical Engineering and Information Technology
- Beijing Jiaotong University B.Eng. Communication Engineering
Experience
- University of Oxford · VGG Visiting Researcher · DAAD IFI
- Karlsruhe Institute of Technology · CVHCI Research & Teaching Assistant
- Sony Electronics Research Intern
Research Interests
- Document AIDocument analysis, reasoning, understanding and multimodal intelligence
- Computer VisionRobust multimodal perception and visual reasoning
- Assistive Visual IntelligenceVision systems for visually impaired individuals
Recent News
All publications- Three papers (Seeing Together, Read, Parse, Describe, and VL-DocIR) have been accepted by NeurIPS 2026.
- A paper (IMPACT) has been accepted by ACM MM 2026.
- Two papers (WanderDream, InterEdit) have been accepted by ECCV 2026.
- Two papers (RHO, PanoVQA) have been accepted by CVPR 2026.
- A paper (MICA) has been accepted by ICRA 2026.
- A paper (HybriDLA) has been selected as Oral by AAAI 2026.
Selected Publications
View allVL-DocIR: A Benchmark for Vision-Based Long Document Retrieval
Simon Ott, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen
HybriDLA: Hybrid Generation for Document Layout Analysis
Yufan Chen, Omar Moured, Ruiping Liu, Junwei Zheng, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen
Graph-based Document Structure Analysis
Yufan Chen, Ruiping Liu, Junwei Zheng, Di Wen, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen
SFDLA: Source-Free Document Layout Analysis
Sebastian Tewes, Yufan Chen, Omar Moured, Jiaming Zhang, Rainer Stiefelhagen
RoDLA: Benchmarking the Robustness of Document Layout Analysis Models
Yufan Chen, Jiaming Zhang, Kunyu Peng, Junwei Zheng, Ruiping Liu, Philip Torr, Rainer Stiefelhagen