📄 论文总结
VisMem：潜在视觉记忆释放视觉语言模型潜力 / VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
1️⃣ 一句话总结
这篇论文提出了一种名为VisMem的认知对齐框架，通过为视觉语言模型添加短期和长期视觉记忆模块，解决了模型在处理复杂视觉任务时容易丢失细节和语义一致性的问题，从而显著提升了模型性能。
🤖 系统
Abstract - VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a deficit in contextualized visual experience during prolonged generation. Drawing inspiration from human cognitive memory theory, which distinguishes short-term visually-dominant memory and long-term semantically-dominant memory, we propose VisMem, a cognitively-aligned framework that equips VLMs with dynamic latent vision memories, a short-term module for fine-grained perceptual retention and a long-term module for abstract semantic consolidation. These memories are seamlessly invoked during inference, allowing VLMs to maintain both perceptual fidelity and semantic consistency across thinking and generation. Extensive experiments across diverse visual benchmarks for understanding, reasoning, and generation reveal that VisMem delivers a significant average performance boost of 11.8% relative to the vanilla model and outperforms all counterparts, establishing a new paradigm for latent-space memory enhancement. The code will be available: this https URL.