MI-Pruner Cuts 89% of Image Tokens While Preserving 97% Accuracy
MI-Pruner selects which image tokens to drop by measuring how much each token shares with the text prompt, without reading attention maps. This lets it be added to off-the-shelf multimodal models while keeping 97% accuracy.
Read the full story at AlphaSignal ↗
Timeline · 1 report
- 2026-11-18 18:01 · AlphaSignal
MI-Pruner Cuts 89% of Image Tokens While Keeping 97% AI Accuracy