ATM-Bench
According to Me: Long-Term Personalized Referential Memory QA
Jingbiao Mei, Jinghong Chen, Guangyu Yang, Xinyu Hou, Margaret Li, Bill Byrne · 2026-03-02
- Modality
- Image
- Data
- Real data
- Task · ground truth
- QA/Ret. · Ans.+Ev.
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesDirectly evaluated
- UQUnanswerable queriesDirectly evaluated
- MAMemory-grounded actionNot evaluated
- FGFine-grained visual detailDirectly evaluated
- ETEntity trackingDirectly evaluated
- VCVisual state changeDirectly evaluated
Survey notes
Personal-memory queries require retrieval from a multi-year multimodal archive, with evidence annotations, multi-source composition and changes over time.