Scaling Laws of Large Vision-Language Models on Cross-Domain Benchmarks

This report synthesises findings from 16 peer-reviewed papers addressing the following research question: How does the performance of LVLMs scale with increasing model size when evaluated on LVLM-eHub's cross-domain tasks, and what is the optimal model size for balanced accuracy and efficiency. 10 claims were extracted from source literature; 10 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 9.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the performance of LVLMs scale with increasing model size when evaluated on LVLM-eHub's cross-domain tasks, and what is the optimal model size for balanced accuracy and efficiency?

Autonomous literature synthesis. Automated review score: 9.3/10. Full text and citation available at Assignee Research.