TeleEgo
TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
Jiaqi Yan, Ruilong Ren, Jingren Liu, Shuning Xu, Ling Wang, Yiheng Wang, et al. · 2025-12-10
- Modality
- Video & streaming
- Data
- Real data
- Task · ground truth
- QA · Ans.+Time
- Scope
- Benchmark with memory tracks
What it tests
- CECross-modal evidenceDirectly evaluated
- LELong-range evidenceDirectly evaluated
- SCState changesDirectly evaluated
- CFConflicting memoriesNot evaluated
- UQUnanswerable queriesNot evaluated
- MAMemory-grounded actionNot evaluated
- TLTemporal localizationDirectly evaluated
- TRTemporal relationsDirectly evaluated
- MEMulti-event integrationDirectly evaluated
Survey notes
Multi-day egocentric streams include explicit short-, long- and ultra-long recall and cross-memory reasoning under an online protocol.