Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors

arXiv:2607.15689v1 Announce Type: new Abstract: Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames seemingly requires understanding the video first. We resolve this circular dependency with a simple observation: cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generatio...