AI RESEARCH
The Model Knows Which Tokens Matter: Automatic Token Selection via Noise Gating
arXiv CS.CV
•
ArXi:2603.07135v1 Announce Type: new Visual tokens dominate inference cost in vision-language models (VLMs), yet many carry redundant information. Existing pruning methods alleviate this but typically rely on attention magnitude or similarity scores. We reformulate visual token pruning as capacity constrained communication: given a fixed budget K, the model must allocate limited bandwidth to maximally preserve visual information.