Multilingual Few-shot Document Layout Analysis

Research topic/area

Document Analysis, Deep Learning, Computer Vision, Artifical Intelligence

Type of thesis

Master

Start time

-

Application deadline

31.05.2026

Duration of the thesis

-

Description

Document Layout Analysis (DLA) has made great strides in high-resource languages (like English and Chinese) But remains challenging for low-resource languages due to scarce labeled data. State-of-the-art models such as LayoutLM achieve strong results on English documents; however, they struggle to generalize to languages like Tamil, Urdu, or Amharic that were absent or underrepresented in training. In this thesis, we will research multilingual modeling and transfer learning to tackle DLA in low-resource languages. We will explore how multilingual document models (e.g., LayoutXLM, LayoutLMv3) pre-trained on rich-resource languages can be adapted through few-shot learning to perform layout analysis in new languages.

What you do:
● Literature research on DLA and few-shot learning.
● Dataset creation with DLA task in low-resource languages.
● Implementation of state-of-the-art methods for multilingual DLA tasks.

What we offer:
● Getting started quickly with our open-source code
● Compute resources for model training and deployment
● Experienced guidance and open discussions with other team members
● Support publishing your work at top conferences (also attending conferences in person)

Further Information:
We have further topics, such as Computer Vision, large language models (LLMs), Generative Models, Retrieval-Augmented Generation (RAG), Document Analysis and understanding, etc.

Please feel free to contact me (yufan.chen@kit.edu) with your CV and transcript of your records.

Requirement

Requirements for students

• Interest in the topic of computer vision and doing task-oriented research
• Python programming skills and knowledge of PyTorch/Tensorflow are desirable

Faculty departments

• Engineering sciences
  Electrical engineering & information technologies
  Geodesy & geoinformatics
  Informatics
  Mechatronics & information technologies
  Other fields of study
  Remote Sensing and Geoinformatics
  Information System Engineering and Management

Supervision

Title, first name, last name

Msc., Yufan, Chen

Organizational unit

Computer Vision for Human-Computer Interaction Lab, Institute for Anthropomatics and Robotics (IAR)

Email address

yufan.chen@kit.edu

Link to personal homepage/personal page

Website

Application via email

Application documents

• Curriculum vitae
• Grade transcript

E-Mail Address for application
Senden Sie die oben genannten Bewerbungsunterlagen bitte per Mail an yufan.chen@kit.edu


Back