Personal Visual Memory from Explicit and Implicit Evidence
2026-05-27 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputation and LanguageInformation Retrieval
AI summaryⓘ
The authors created a new test to help AI remember personal details better by using pictures, not just text. They point out that images can show unique or hidden personal information that text might miss. Their new system, VisualMem, keeps track of important visual facts linked to people and objects instead of turning images into simple captions. Tests show that VisualMem works better than older systems at remembering personal visual info while still doing well with text memory tasks.
long-term memorypersonalized AI agentsvisual memorymultimodal cuesbenchmarkVisualMemtext-memoryuser-specific informationidentity resolutionconversational context
Authors
Viet Nguyen, Thao Nguyen, Vishal M. Patel, Yuheng Li
Abstract
Long-term memory is increasingly important for personalized AI agents, yet existing benchmarks and methods remain largely text-centric. Even when images are included, the user-specific information needed for later questions is typically recoverable from text alone, and most memory systems reduce image turns to generic captions. Yet images often carry personal information that text rarely states -- both explicit evidence, such as recurring user-associated entities, and implicit evidence, such as latent user facts inferred from visual or multimodal cues. We introduce a benchmark for personal visual memory that targets both forms of evidence, and propose VisualMem, a hybrid visual--text architecture that augments a text-memory backend with a structured personal visual memory module. Rather than collapsing images into captions, VisualMem uses conversational context to resolve identity, ownership, and durable user facts. Experiments show that VisualMem substantially outperforms prior memory systems on our benchmark while remaining competitive on standard text-memory benchmarks, indicating that personal visual memory is a distinct and important component of long-term memory for personalized AI agents.