visual-attribution

Tag

Cards List
#visual-attribution

VAD: Attributing Visual Evidence for Target Reconstruction in Multimodal On-Policy Distillation

Hugging Face Daily Papers · 2026-07-30 Cached

Introduces Visual Attribution Distillation (VAD), a counterfactual target-reconstruction method for multimodal on-policy distillation that estimates the visually-attributable part of teacher corrections. Outperforms existing approaches across fine-grained visual benchmarks at 4B and 9B scales.

0 favorites 0 likes
← Back to home

Submit Feedback