arXivShaden Shaar, Bradon Thymes, Majd Aldaye, Claire Cardie, Bharath HariharanFri, Oct 30, 2026, 2:05 PM PDT
score 14.8
New benchmark tests AI on hours-long video reasoning
Original: LF-VideoQA: Evaluating Long-Video Understanding with Long-Form Theory-of-Mind Questions
Source: arxiv.org ↗
Writing ELI5 summary…