面向视觉-语言推理的分解式在策略蒸馏：引导梯度实现视觉定位
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
AI总结：
通过将视觉-语言模型蒸馏损失分解为语言先验和视觉定位两个正交分量，提出视觉梯度引导（VGS）方法动态调整更新方向以优先优化视觉子空间，从而提升小模型在复杂多模态任务中的定位能力。
摘要：
虽然在策略蒸馏为训练小型推理模型提供了密集监督，但其在多模态领域的优化动态仍未得到充分探索。在这项工作中，我们通过数学上将损失分解为两个不同的组成部分：语言先验和视觉定位，挑战了视觉-语言模型（VLM）蒸馏的标准整体观点。我们的分析揭示，这些分量的梯度向量几乎正交，表明与教师语言分布对齐的目标在几何上独立于匹配其视觉感知的目标。因此，标准优化被动地遵循一条次优的折衷轨迹，隐式地平衡这两个目标。假设视觉定位是视觉-语言推理的主要瓶颈，我们引入了视觉梯度引导（VGS），一种动态重新定向更新向量以优先考虑视觉子空间的方法。在多个蒸馏设置和复杂多模态基准上的实验结果表明，VGS显著优于标准的在策略蒸馏整体公式，以最小的训练开销实现了卓越的定位能力。
英文摘要：
While on-policy distillation offers dense supervision for training small reasoning models, its optimization dynamics in the multimodal domain remain under-explored. In this work, we challenge the standard monolithic view of Vision-Language Model (VLM) distillation by mathematically decomposing the loss into two distinct components: the language prior and visual grounding. Our analysis uncovers that gradient vectors for these components are nearly orthogonal, indicating that the objective of aligning with the teacher's language distribution is geometrically independent from the objective of matching its visual perception. Consequently, standard optimization passively follows a suboptimal compromise trajectory that implicitly balances the two objectives. Hypothesizing that visual grounding constitutes the primary bottleneck for vision-language reasoning, we introduce Visual Gradient Steering (VGS), a method that dynamically reorients the update vector to prioritize the visual subspace. Experimental results on multiple distillation settings and complex multimodal benchmarks demonstrate that VGS significantly outperforms the standard monolithic formulation of on-policy distillation, achieving superior grounding with minimal training overhead.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
