We invite researchers, practitioners, and enthusiasts to contribute to the Workshop and Grand Challenge on Large Vision–Language Model Learning and Applications (LAVA), to be held in conjunction with ACM Multimedia 2025.

🔬 LAVA Workshop Overview

The LAVA Workshop explores innovations and challenges in Large Vision–Language Models (LVLMs). We welcome contributions across a broad spectrum of topics, including but not limited to:

• Data preprocessing and prompt engineering for LVLMs
• Training and compression techniques for LVLMs
• Self-supervised, unsupervised, few-shot, and zero-shot learning
• Generative AI and multimodal generation
• Trustworthy and explainable LVLMs
• Security, privacy, and ethical concerns in LVLMs
• Evaluation and benchmarking methodologies
• LVLMs for downstream tasks and applications
• LVLMs in virtual, augmented, and mixed reality
• LVLMs for low-resource scenarios
• Multimodal integration beyond vision and language

Submission Types

• Short papers (non-archived): Up to 4 pages, excluding references
• Long papers (archived in ACM Digital Library): Up to 8 pages, excluding references

All submissions should follow the official ACM MM format.

Workshop Important Dates

• 📄 Paper submission deadline: June 15, 2025
• 🚀 ACM MM fast-track submission: July 11, 2025
• ✅ Notification of acceptance: July 24, 2025
• 🖋️ Camera-ready deadline: August 1, 2025
• 📅 Workshop date: October 27–28, 2025

🔗 More info: https://lava-workshop.github.io/workshop

🏆 LAVA Grand Challenge 2025

This year's LAVA Challenge focuses on enhancing LVLM capabilities in interpreting complex visual documents, including: Data Flow Diagrams (DFDs), Class Diagrams, Gantt Charts, Architectural and Building Design Drawings

The 2025 challenge emphasizes Japanese government and business documents in PDF format, each accompanied by multiple-choice (10-option) questions requiring deep visual–linguistic understanding.

Challenge Important Dates

• ✅ Registration opens: March 15, 2025
• 📂 Public data release: April 17, 2025
• ⏳ Registration closes: May 31, 2025
• 🔐 Private test data release: We decided to use the test data for public and private leaderboard.
• 📝 Final results, report & paper submission deadline: June 30, 2025
• 📢 Notification of acceptance: July 24, 2025
• 🖋️ Camera-ready deadline: August 26, 2025
• 📅 Challenge presentation date: October 27–31, 2025

🔗 More info: https://lava-workshop.github.io/grandchallenge

We look forward to your contributions and participation in pushing the frontiers of vision–language learning!