PolicyShiftGuard, trained with randomized policy SFT plus matched pass/block boundary pairs, reaches 76.9 Avg. F1 and 72.1 Avg. PSS on a new policy-shift image-guardrail benchmark where existing VLMs stay brittle.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.
citing papers explorer
-
PolicyShiftGuard: Benchmarking and Improving Policy-Adaptive Image Guardrails
PolicyShiftGuard, trained with randomized policy SFT plus matched pass/block boundary pairs, reaches 76.9 Avg. F1 and 72.1 Avg. PSS on a new policy-shift image-guardrail benchmark where existing VLMs stay brittle.
-
From Heads to Neurons: Causal Attribution and Steering in Multi-Task Vision-Language Models
HONES ranks feed-forward neurons by their causal contributions from task-relevant attention heads and uses lightweight scaling to steer performance on multiple vision-language tasks.