FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion
Researchers have introduced FadeMem, a novel memory consolidation technique for autoregressive video generation models. This method addresses the issue of growing historical KV cache sizes in models that generate videos segment by segment. FadeMem organizes historical data into a temporal hierarchy, preserving fine details in recent segments while consolidating older information into more compact, long-range anchors for scene structure and identity. AI
IMPACT Enhances video generation models by optimizing memory usage and improving temporal coherence and subject consistency.