STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient Large Vision-Language Models

תקציר מקורי באנגליתarXiv:2609.05916v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but the hundreds to thousands of visual tokens they process impose substantial computational overhead, motivating training-free visual token pruning. In this work, we conduct two complementary analyses of visual token pruning. First, we measure the feature-space coverage of tokens retained before cross-modal fusion and find that aggressive pruning discards substantial visual information. Second, we track text-to-visual attention across decoder layers and find that the visual tokens considered important change substantially with depth, making one-shot pruning decisions unreliable. Together, these findings show that effective pruning should preserve broad visual cov