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.
Pixel reasoner: Incentivizing pixel-space reasoning with curiosity-driven reinforcement learning
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.