TeleEgo: Benchmarking Egocentric AI Assistants in the Wild
This provides a comprehensive evaluation framework for researchers developing practical AI assistants, though it is incremental as it builds on existing benchmark concepts.
The paper tackles the lack of realistic benchmarks for egocentric AI assistants by introducing TeleEgo, a long-duration, streaming, omni-modal dataset with over 14 hours per participant of synchronized data across four domains, resulting in 3,291 human-verified QA items and new metrics for evaluation.
Egocentric AI assistants in real-world settings must process multi-modal inputs (video, audio, text), respond in real time, and retain evolving long-term memory. However, existing benchmarks typically evaluate these abilities in isolation, lack realistic streaming scenarios, or support only short-term tasks. We introduce \textbf{TeleEgo}, a long-duration, streaming, omni-modal benchmark for evaluating egocentric AI assistants in realistic daily contexts. The dataset features over 14 hours per participant of synchronized egocentric video, audio, and text across four domains: work \& study, lifestyle \& routines, social activities, and outings \& culture. All data is aligned on a unified global timeline and includes high-quality visual narrations and speech transcripts, curated through human refinement.TeleEgo defines 12 diagnostic subtasks across three core capabilities: Memory (recalling past events), Understanding (interpreting the current moment), and Cross-Memory Reasoning (linking distant events). It contains 3,291 human-verified QA items spanning multiple question formats (single-choice, binary, multi-choice, and open-ended), evaluated strictly in a streaming setting. We propose two key metrics -- Real-Time Accuracy and Memory Persistence Time -- to jointly assess correctness, temporal responsiveness, and long-term retention. TeleEgo provides a realistic and comprehensive evaluation to advance the development of practical AI assistants.