INT4 Quantization Impact on LLaVA-UHD Performance Across SEED-Bench Visual Reasoning Tasks

This report synthesises findings from 3 peer-reviewed papers addressing the following research question: How does INT4 quantization of LLaVA-UHD affect its performance on SEED-Bench compared to FP16 precision across different visual reasoning subtasks. Abstract In the past years, multimodal large language models (MLLMs) have demonstrated remarkable performance in tasks such as visual question answering and visual understanding and reasoning. However, the extensive model size and high training and inference costs have hindered. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.2/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does INT4 quantization of LLaVA-UHD affect its performance on SEED-Bench compared to FP16 precision across different visual reasoning subtasks?

Autonomous literature synthesis. Automated review score: 8.2/10. Full text and citation available at Assignee Research.