CPPO：基于对比感知的视觉语言策略优化

摘要

我们提出CPPO（对比感知策略优化方法），用于微调视觉语言模型。虽然强化学习在语言模型的推理能力方面取得了进展，但将其扩展到多模态推理需要同时提升感知与推理能力。先前研究主要通过显式感知奖励应对这一挑战，但分离感知标记与推理标记存在困难——需要额外的大语言模型支持、真实标注数据、通过策略模型强制分离感知与推理，或对所有输出标记 indiscriminately 施加奖励。CPPO通过分析输入图像扰动下模型输出的熵值变化来检测感知标记，进而将对比感知损失引入强化学习目标函数：该损失函数要求在信息保留型扰动下保持输出一致性，在信息消除型扰动下体现敏感性。实验表明，CPPO在避免使用额外模型的前提下超越了既有感知奖励方法，使训练更具效率与可扩展性。

English

We introduce CPPO, a Contrastive Perception Policy Optimization method for finetuning vision-language models (VLMs). While reinforcement learning (RL) has advanced reasoning in language models, extending it to multimodal reasoning requires improving both the perception and reasoning aspects. Prior works tackle this challenge mainly with explicit perception rewards, but disentangling perception tokens from reasoning tokens is difficult, requiring extra LLMs, ground-truth data, forced separation of perception from reasoning by policy model, or applying rewards indiscriminately to all output tokens. CPPO addresses this problem by detecting perception tokens via entropy shifts in the model outputs under perturbed input images. CPPO then extends the RL objective function with a Contrastive Perception Loss (CPL) that enforces consistency under information-preserving perturbations and sensitivity under information-removing ones. Experiments show that CPPO surpasses previous perception-rewarding methods, while avoiding extra models, making training more efficient and scalable.

CPPO：基于对比感知的视觉语言策略优化

CPPO: Contrastive Perception for Vision Language Policy Optimization

摘要

Support