A reasoning-prefix masking strategy during VLM distillation encourages students to anchor their thinking on visual evidence, yielding better multimodal reasoning than prior distillation baselines.
Measuring mathematical problem solving with the math dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
A reasoning-prefix masking strategy during VLM distillation encourages students to anchor their thinking on visual evidence, yielding better multimodal reasoning than prior distillation baselines.