Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation 事件

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation arXiv:2605.11651v4 Announce Type: replace Abstract: Recent think-answer approaches in VLMs, such as Qwen3-VL-Thinking, boost reasoning performance by leveraging intermediate thinking steps before the final answer, but their computational cost becomes substantial, especially for larger VLMs. To distill such capabilities into compact think-answer VLMs, a primary objective is to improve the student's ability to