LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception
arXiv:2609.39938v2 Announce Type: replace-cross Abstract: Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression severely dilutes fine-grained acoustic and visual evidence. We introduce LEAP, a framework where the model retrieves its own evidence without placing the whole recording in one context. LEAP divides a recording into fixed-duration blocks, applying a lightweigh…