GRPO and PPO Sample Efficiency in Fine-Tuning LLaVA-UHD on SEED-Bench-R1

This report synthesises findings from 9 peer-reviewed papers addressing the following research question: How does the sample efficiency of GRPO compare to PPO when fine-tuning LLaVA-UHD variants on SEED-Bench-R1 across different parameter scales. Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities. 9 claims were extracted from source literature; 9 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the sample efficiency of GRPO compare to PPO when fine-tuning LLaVA-UHD variants on SEED-Bench-R1 across different parameter scales?

Autonomous literature synthesis. Automated review score: 8.5/10. Full text and citation available at Assignee Research.