When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
Efficient long-video understanding requires vision--language models (VLMs) to reason over a small number of frames selected as sparse visual evidence. Existing relevance-based methods rely on static one-shot selection with fixed frame budgets and candidate pools, while agent-based schedulers achieve adaptivity through costly multi-round reasoning and interactive search. We propose EcoFrame, a…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
