frontier models
Long-Video Memory Followed Objects Across Days
Grounded Entity Biographies linked the same physical instance across clips without discarding each moment's context.
Summary
Grounded Entity Biographies linked the same physical instance across clips without discarding each moment's context.
Grounded Entity Biographies groups visually grounded observations of one physical object into a retrievable history, then supplies that biography alongside episodic evidence when answering questions. Across four benchmarks containing day- and week-long recordings, the authors report improvements for both multiple-choice and open-ended answers. On EgoLifeQA, accuracy reached 72.0%, 4.4 percentage points above the best published result cited in the paper. Ablations attribute gains to both identity association and biography reading; extra descriptions alone did not recover the full improvement.
Why it matters
Grounded Entity Biographies linked the same physical instance across clips without discarding each moment's context.
Limits and context
- Ablations attribute gains to both identity association and biography reading; extra descriptions alone did not recover the full improvement.
Key claims
Grounded Entity Biographies linked the same physical instance across clips without discarding each moment's context.
Qualification: Ablations attribute gains to both identity association and biography reading; extra descriptions alone did not recover the full improvement.
Evidence: source-2026-09-30-010
Sources
- arXiv preprint 2609.38155arXiv · primary research
Corrections
No corrections have been recorded for this story.