PolarMem: 一种无需训练的可验证视觉语言模型极化隐式图记忆
PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
AI总结：
提出PolarMem，一种无需训练的极化隐式图记忆框架，通过语义一致性验证和自适应分布划分将视觉语言模型感知信号转化为HAS、NOT_HAS和Uncertain记忆状态，并采用词典逻辑感知检索协议优先保证逻辑一致性，从而提升检索密集型任务性能并减少矛盾。
摘要：
记忆对于智能系统而言不仅是存储机制，更是组织证据和约束信念的结构。这对多模态推理尤为重要，因为检索到的证据必须既与查询相关又在视觉上一致。然而，当前视觉语言模型（VLM）的记忆系统大多保持正关联：它们检索相似或先前观察到的内容，但缺乏明确的方式记住已被验证为不存在或逻辑排除的内容。为此，我们提出 extbf{PolarMem}，一种无需训练的极化隐式图记忆框架，用于可验证的视觉语言推理。PolarMem通过语义一致性验证和自适应分布划分，将冻结的VLM感知信号转化为 extit{HAS}、 extit{NOT\_HAS}和 extit{Uncertain}记忆状态，并将其存储在具有明确正负记忆关系的极化图中。在推理时，词典逻辑感知检索协议在语义相似性之前强制执行逻辑一致性，在冲突记忆进入模型上下文之前将其抑制。在八个冻结的VLM骨干网络和六个多模态基准测试中，PolarMem一致地提升了检索密集型任务性能并减少了检索级矛盾。这些结果凸显了负记忆作为构建更可靠多模态记忆系统的关键机制。我们的代码可在https://github.com/czs-ict/PolarMem获取。
英文摘要：
Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reasoning, where retrieved evidence must be both query-relevant and visually consistent. However, current memory systems for vision-language models (VLMs) remain largely positive-associative: they retrieve what is similar or previously observed, but lack an explicit way to remember what has been verified as absent or logically excluded. To this end, we propose \textbf{PolarMem}, a training-free polarized latent graph memory framework for verifiable vision-language reasoning. PolarMem transforms frozen VLM perceptual signals into \textit{HAS}, \textit{NOT\_HAS}, and \textit{Uncertain} memory states through semantic consistency verification and adaptive distributional partitioning, and stores them in a polarized graph with distinct positive and negative memory relations. During inference, a lexicographical logic-aware retrieval protocol enforces logical consistency before semantic similarity, suppressing conflicting memories before they enter the model context. Across eight frozen VLM backbones and six multimodal benchmarks, PolarMem consistently improves retrieval-intensive tasks and reduces retrieval-level contradictions. These results highlight negative memory as a key mechanism for building more reliable multimodal memory systems. Our code is available at https://github.com/czs-ict/PolarMem.
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。
