← Back to research

Research Brief · 2026-11-11 Supporting

MemInStream: Memorizing or Merely Recognizing? Rethinking Streaming Video Memory Evaluation

The idea, in brief

A streaming video memory test that keeps only questions needing evidence from earlier in the stream. Online models answer under 40% of them.

Editorial summary · not the author abstract. Read the linked paper for the complete abstract and claims.
Figure 1: models fail even with the evidence available, memory necessity is checked against recent frames and text alone, and an evidence-controlled protocol builds the benchmark.
Figure 1: models fail even with the evidence available, memory necessity is checked against recent frames and text alone, and an evidence-controlled protocol builds the benchmark. Original figure · paper authors ↗

Release evidence

Evaluation adapters and scoring for about nine methods are public, with annotations in the repository and the videos (about 310 GB) on Hugging Face.

Last checked · 2026-11-15