CVPD finds visual blind spots by comparing a model's own crop, full-image, and ghosted responses, then uses the crop as a positive teacher and the ghost as a negative teacher for dense self-distillation.
On-policy distillation of language models: Learning from self-generated mistakes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Perception Before Supervision: Self-Contained Visual Distillation from Counterfactual Blind Spots
CVPD finds visual blind spots by comparing a model's own crop, full-image, and ghosted responses, then uses the crop as a positive teacher and the ghost as a negative teacher for dense self-distillation.