Preprint
Jul 2026
Homer: Understanding Long-form Videos with Hierarchical Memory and Agentic Reasoning
A Hierarchical Online Memory Exploration and Reasoning framework that mirrors the multi-scale structure of long videos, and consistently lifts three various LLM backbones, indicating a model-agnostic structural capability for grounded retrieval over long videos.
Yixin Ji, F. Ye, Juntao Li et al.
· 1 citation