ELViM
video-SALMONN S: Memory-Enhanced Streaming Audio-Visual LLM
Guangzhi Sun, Yixuan Li, Xiaodong Wu, Yudong Yang, Wei Li, Zejun Ma, et al. · 2026-02-03
- 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
Procedural video evidence is followed by distractors and later next-action questions, testing retention and reuse of earlier demonstrations.