TensorX
返回文献探索

Paper · arXiv 2605.22718

WorldKV: Efficient World Memory with World Retrieval and Compression

Jung Yi, Minjae Kim, Paul Hyunbin Cho, Wooseok Jang, Sangdoo Yun, Seungryong Kim

44 upvotesMay 21, 2026arXiv 预印本
AI 摘要

WorldKV enables persistent world generation in video diffusion models by retrieving and compressing key-value cache chunks to maintain consistency while improving throughput.

autoregressive video diffusion modelsKV-cache attentionsliding window inferenceworld retrievalworld compressionkey-key similarityattention windowtoken pruningcamera/action correspondence

Abstract

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full KV-cache attention preserves this consistency but breaks real-time constraints: memory footprint and attention cost grow linearly with rollout length. Sliding window inference restores throughput but discards long-term consistency. We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression. World Retrieval stores evicted KV-cache chunks in GPU/CPU memory and selectively retrieves scene-relevant chunks via camera/ action correspondence, inserting them back into the native attention window without re-encoding. World Compression prunes redundant tokens within each chunk via key-key similarity to an anchor frame, halving per-chunk storage to fit 2x more history under a fixed budget. On Matrix-Game-2.0 and LingBot- World-Fast, WorldKV matches or exceeds full-KV memory fidelity at roughly 2x the throughput, and is competitive with memory-trained baselines without any fine-tuning. Project Page: https://cvlab-kaist.github.io/WorldKV/

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
WorldKV: Efficient World Memory with World Retrieval and Compression | TensorX