LAVA-Workshop

Workshop Call for Papers Challenge Schedule Speakers Organizers

There has been significant advancement in AI and machine learning, particularly with the development of large language models like GPT recently. These models have demonstrated their prowess in harnessing extensive text data to achieve remarkable performance across various natural language understanding tasks. As a result, there is a growing interest in expanding these capabilities to encompass additional modalities such as images, audios, and videos, giving rise to large vision-language models (LVLMs) like GPT-V. LAVA workshop aims to unleash the full potential of research in large vision-language models (LVLMs) by emphasizing the convergence of diverse modalities, including text, images, and video. Furthermore, the workshop provides a platform for delving into the practical applications of LVLMs across a broad spectrum of domains, such as healthcare, education, entertainment, transportation, finance, etc.

Call for Papers

We welcome people to submit papers about large vision-language models (LVLMs) to LAVA workshop. Accepted papers will be presented in our workshop and will be published in the ACCV workshop proceeding. We accept short papers (non-archived) which are up to 7 pages in ACCV format, excluding references; and long papers (archived) which are up to 14 pages in ACCV format, excluding references. Submission policies adhere to the ACCV submission policies.

The topics in this workshop will include but are not limited to:

Data preprocessing and prompt engineering in LVLMs
Training/Compressing LVLMs
Self-supervised and/or unsupervised, few-/zero-shot learning in LVLMs
Generative AI
Trust-worthy/Explainable LVLMs learning
Security and privacy in LVLMs
LVLMs evaluation and benchmarking
LVLMs for downstream tasks
LVLMs in virtual reality, mixed reality
Applications of LVLMs
LVLMs and other modalities
LVLMs for low resources

Submit your paper here.

LAVA Challenge

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 workshop challenge. Participants can register as individuals or teams. They are required to develop a model that can answer questions related to the input data. Below, we provide a few samples.

Datasets:

Public dataset: We will release our dataset collected from the internet. It contains about 3,000 samples.
Private dataset: The TASUKI team (SoftBank) provides this dataset. It contains about 1,100 samples.

The data contain English and Japanese texts. You can download the data here. Please carefully read the Terms and Conditions for further information about the license, data, and submission instructions.

Participants are required to submit the results to our system to get the scores.

Register your team information here. We will send the link to download the dataset to registered participants.

Metric:
We will evaluate using MMMU.
Final score = 0.3 * Public dataset + 0.7 * Private dataset
Prizes and Travel Grants:Travel grants are available for winning teams (one per team). Prizes will be announced later.
Computational Resources:Participants from the University of Tokyo may use SoftBank Beyond AI SANDBOX GPUs.

Submit your report here.
Submit your results here

Important Dates