VLM memory survey from 8 institutions: 4D taxonomy covering 300+ papers and ~70 benchmarks

机器之心 · wechat · 2026-11-16

Researchers from Duke, Google, USC, UPenn, UNC and four other institutions released a systematic survey of memory in vision-language models, organizing 300+ papers and 70 benchmarks under a new 4D taxonomy.

Paper and curated paper list are open-sourced on GitHub.

Original post →

More from Research

Research channel →