Proposes reasoning-prefix masking during VLM distillation to anchor student thinking on visual evidence and improve multimodal reasoning in smaller models.
Vl-rethinker: Incentivizing self-reflection of vision-language models with 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
No citing papers match the current filters.