VisMem: 通过潜在视觉记忆解锁视觉-语言模型的潜力
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
AI总结：
VisMem通过引入动态潜在视觉记忆模块，提升视觉-语言模型在复杂视觉任务中的性能，实现感知准确性和语义一致性之间的平衡。
摘要：
尽管视觉-语言模型（VLMs）在许多复杂视觉任务上取得了显著成功，但其性能常常受到一个
英文摘要：
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 11.0% relative to the vanilla model and outperforms all counterparts, establishing a new paradigm for latent-space memory enhancement. The code will be available: https://github.com/YU-deep/VisMem.git.
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。
