AIBullisharXiv – CS AI · Feb 277/107
🧠
Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models
Researchers introduce Spatial Credit Redistribution (SCR), a training-free method that reduces hallucination in vision-language models by 4.7-6.0 percentage points. The technique redistributes attention from dominant visual patches to contextual areas, addressing the spatial credit collapse problem that causes AI models to generate false objects.