Visual Skill Cards improve GUI action prediction for frozen and distilled agents by retrieving reusable, state-conditioned visual procedures.
Vision-OPD: Learning to See Fine Details for Multimodal
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SkillLens: Visual Skill Cards for Retrieval-Augmented GUI Action Prediction and On-Policy Distillation
Visual Skill Cards improve GUI action prediction for frozen and distilled agents by retrieving reusable, state-conditioned visual procedures.