Salvato in:
Dettagli Bibliografici
Autori principali: Chen, Zhisheng, Wu, Tingyu, Zhou, Zijie, Xie, Zhengwei, Li, Jinhan, Weng, Ziyan, Lin, Liang, Song, Jingwei, Xiao, Zikai, Zhang, Yingwei
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.00415
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910274733211648
author Chen, Zhisheng
Wu, Tingyu
Zhou, Zijie
Xie, Zhengwei
Li, Jinhan
Weng, Ziyan
Lin, Liang
Song, Jingwei
Xiao, Zikai
Zhang, Yingwei
author_facet Chen, Zhisheng
Wu, Tingyu
Zhou, Zijie
Xie, Zhengwei
Li, Jinhan
Weng, Ziyan
Lin, Liang
Song, Jingwei
Xiao, Zikai
Zhang, Yingwei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_00415
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
Chen, Zhisheng
Wu, Tingyu
Zhou, Zijie
Xie, Zhengwei
Li, Jinhan
Weng, Ziyan
Lin, Liang
Song, Jingwei
Xiao, Zikai
Zhang, Yingwei
Artificial Intelligence
Machine Learning
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.
title PolarMem: A Training-Free Polarized Latent Graph Memory for Verifiable Vision-Language Models
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2602.00415