Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance Prediction

Computer Science > Computer Vision and Pattern Recognition arXiv:2609.13225 (cs) [Submitted on 1 Sep 2026] Title: Part Grounding, Not Action Knowledge: Locating the Bottleneck in VLM Affordance Prediction Authors: Sarthak Sattigeri View a PDF of the paper titled Part Grounding, Not Action Knowledge: