Showing 2025Show all
2 papers · 1 filter
cs.CV2025
Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
Chaoyang Wang, Yangfan He, Yiyang Zhou +6
We reveal a critical yet underexplored flaw in Large Vision-Language Models (LVLMs): even when these models know the correct answer, they frequently arrive there through incorrect…
cs.LG2025
Effective Model Pruning: Measure The Redundancy of Model Components
Yixuan Wang, Dan P. Guralnik, Saiedeh Akbari +1
This article initiates the study of a basic question about model pruning. Given a vector of importance scores assigned to model components, how many of the scored components co…