SLVMBench
SLVMBench: Skill Learning from Video Memory
Yudong Yang, Guangzhi Sun, Yixuan Li, Chao Zhang · 2026-07-13
- Modality
- Video & streaming
- Data
- Real data
- Task · ground truth
- QA/Learn · Ans.+Time
- Scope
- Memory-specific benchmark
What it tests
- CECross-modal evidencePartially evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesPartially evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionDirectly evaluated
- TLTemporal localizationDirectly evaluated
- TRTemporal relationsDirectly evaluated
- MEMulti-event integrationDirectly evaluated
Survey notes
Earlier instructional video must support later questions in another stream after distractors and a temporal gap.