FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion 事件

FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion arXiv:2606.10671v1 Announce Type: new Abstract: Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length. Existing bounded-cache methods reduce this cost with local windows, sink tokens, or compressed memory states, yet they usually assign fixed roles to different parts of the history. We propose FadeMem, a distance-aware