AI RESEARCH
Foveated Reasoning: Stateful, Action-based Visual Focusing for Vision-Language Models
arXiv CS.CV
•
ArXi:2604.21079v1 Announce Type: new Vision-language models benefit from high-resolution images, but the increase in visual-token count incurs high compute overhead. Humans resolve this tension via foveation: a coarse view guides "where to look", while selectively acquired high-acuity evidence refines "what to think". We