{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"WorldKV: Efficient World Memory with World Retrieval and Compression","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/1ceb95e4\"></iframe>","width":"100%","height":180,"duration":1351,"description":"\n            🤗 Upvotes: 29 | cs.CV\n\n            Authors:\n            Jung Yi, Minjae Kim, Paul Hyunbin Cho, Wooseok Jang, Sangdoo Yun, Seungryong Kim\n\n            Title:\n            WorldKV: Efficient World Memory with World Retrieval and Compression\n\n            Arxiv:\n            http://arxiv.org/abs/2605.22718v1\n\n            Abstract:\n            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/\n            ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}