Challenge Overview: The primary goal of this challenge is to advance the capability of Large Vision-Language Models to accurately interpret and understand complex visual data such as Data Flow Diagrams (DFDs), Class Diagrams, Gantt Charts, and Building Design Drawings. We invite AI researchers, data scientists, and practitioners with interest and experience in natural language processing, computer vision, and multimodal learning to join this grand challenge. Participants can register as individuals or teams. They are required to develop a model that can answer questions related to the input data. This year, we invite participants to solve the problem of Japanese government-related and business documents. Each document will be in pdf format which is associated with 10-choice question. We show an example below.
Register your team here!.

Join the challenge through Kaggle page!.

Datasets and Submission guideline:

• Please visit our Kaggle page for detailed information on the dataset and submission format.
• To be eligible for the final evaluation, participants must submit a report along with their solution by the deadline below. Submission of a paper is optional and intended for proceeding publication. Guidelines for report and paper submissions will be provided at a later date.
• We kindly request that the winning teams attend the event in person, as required by the ACMMM organizers.

We note that all data are for research purposes only under CC-BY-NC (商用利用不可) license. We appreciate your understanding and cooporation.

Prizes:Top 3 winner gets up to $1,000 USD for ACMMM 2025 registration fee.
Computational Resources:Participants from the University of Tokyo may use SoftBank Beyond AI SANDBOX GPUs.