Sign inGet started
Paper · arXiv

ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation

On-policy distillation (OPD) improves reasoning by training a student on trajectories sampled from its own policy under supervision from a teacher. In multimodal reasoning, a common extension is to use a privileged teacher that observes training-time-only signals such as reference answers or rationales. However, such answer-side privilege creates a train-test mismatch: the teacher's supervision may depend on signals unavailable to the student, encouraging shortcut imitation rather than visually grounded reasoning. We propose ViCuR, a visually grounded privileged-teacher distillation framework that replaces answer-side privilege with visual cues (query-related evidence in the input). Becau...

AuthorsKanghui Tian, Siyuan Liu, Ziang Yan et al.
Primary categorycs.CV
Published4 June 2026
Last updated at source4 June 2026
cs.CVcs.AIcs.LG
Embed this entry
<iframe src="https://silytics.si/embed/item/a36cd7d4-428c-4420-ac0b-f56e6e343796" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.