Machine Heart
Nov 15, 2026 · Artificial Intelligence
VLM Memory Survey: 4D Taxonomy (When, Where, What, How) for Memory Mechanisms
Researchers from Duke, Google, USC, UPenn, UNC and others present a systematic survey of memory mechanisms in Vision-Language Models, introducing a 4D taxonomy (When, Where, What, How) covering 300+ papers, 70 benchmarks, 8 memory forms, and 8 application scenarios including long-video understanding and embodied navigation.
4D TaxonomyEmbodied NavigationLong Video Understanding
0 likes · 12 min read
