WorldKV: Efficient World Memory with World Retrieval and Compression

• URL: http://arxiv.org/abs/2605.22718v1
• Date: Thu, 21 May 2026 16:55:04 GMT
• Title: WorldKV: Efficient World Memory with World Retrieval and Compression
• Abstract summary: We propose WorldKV, a training-free framework with two components: World Retrieval and World Compression.<n>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.
• Score: 56.57011243315561
• License: http://creativecommons.org/licenses/by/4.0/
• 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/

Related papers

• ReWorld: An Interactive World Model with Long-Horizon Memory [43.24590497177396]
  ReWorld separates control and memory during training and bounds them at inference.<n>A metric-scale-aligned data engine places eight sources -- Unreal-rendered fly-throughs, game roaming, and real-world footage -- on one physical action scale.<n>One backbone serves both a high-fidelity multi-step mode and a real-time interactive one.
  arXiv  Detail & Related papers  (2026-08-24T17:59:05Z)
• Addressable Memory for Video World Models [50.40232922140905]
  We study visual persistence in interactive video world models.<n>We propose WorldTrace, a training-free memory framework for long-horizon visual persistence.
  arXiv  Detail & Related papers  (2026-08-07T16:55:57Z)
• ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning [0.0]
  Long-video question answering requires a model to preserve visual evidence over time without repeatedly reprocessing the same video.<n>A practical approach is to store the vision-language model's internal key-value cache for each video chunk and retrieve that state at query time.<n>However, independently cached video chunks do not compose correctly.<n>This paper presents ChronoStitch, a training method for composing independently stored visual KV memories.
  arXiv  Detail & Related papers  (2026-07-21T19:46:38Z)
• Kamera: Unified Position-Invariant Multimodal KV Cache for Training-Free Reuse [1.081571058570587]
  Multimodal agents repeatedly re-examine the same video frames, UI screenshots, and rendered artifacts as their context window slides.<n>We show this recompute is avoidable, and identify exactly what naive KV reuse loses.<n>Blind reuse therefore leaves single-hop recall intact while halving multi-hop accuracy.<n>We repair it with a small, training-free low-rank conditioning patch stored alongside each position-free chunk.
  arXiv  Detail & Related papers  (2026-06-22T16:47:00Z)
• MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering [75.0394545769057]
  KV-caching stores the Key-Value of the historical tokens via LLM prefill.<n>MuKV is a method that features a multi-grained KV cache compression module and a semi-hierarchical retrieval approach.<n> Experiments on long-streaming VideoQA benchmarks show that MuKV significantly improves answer accuracy, without sacrificing memory and online QA efficiency.
  arXiv  Detail & Related papers  (2026-05-21T10:13:03Z)
• VeriCache: Turning Lossy KV Cache into Lossless LLM Inference [24.571166055469508]
  We present VeriCache, the first inference framework that ensures the same output as full- KV-cache decoding.<n>We show that VeriCache achieves up to 4X higher throughput than full- KV-cache.
  arXiv  Detail & Related papers  (2026-05-17T19:18:39Z)
• KV Cache Quantization for Self-Forcing Video Generation: A 33-Method Empirical Study [0.0]
  We present a comprehensive study of KV-cache compression for self-forcing video generation on a Wan2.1-based Self-Forcing stack.<n>Our study covers 33 quantization and cache-policy variants, 610 prompt-level observations, and 63 benchmark-level summaries.<n>We jointly evaluate peak VRAM, runtime, realized compression ratio, VBench imaging quality, BF16-referenced fidelity (SSIM, LPIPS, PSNR), and terminal drift.
  arXiv  Detail & Related papers  (2026-03-29T01:35:16Z)
• DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity [50.52392445266824]
  We propose a residual-based KV cache compression framework motivated by long-range inter-token similarity and highly shared latent components in KV representations.<n>Instead of discarding tokens, DeltaKV encodes semantic residuals relative to retrieved historical references, preserving fidelity while substantially reducing storage.<n>Experiments show that DeltaKV reduces KV cache memory to 29% of the original while maintaining near-lossless accuracy on LongBench, SCBench, and AIME.
  arXiv  Detail & Related papers  (2026-02-08T15:14:36Z)
• Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization [83.406036390582]
  Quant VideoGen (QVG) is a training free KV cache quantization framework for autoregressive video diffusion models.<n>It reduces KV memory by up to 7.0 times with less than 4% end to end latency overhead.<n>It consistently outperforms existing baselines in generation quality.
  arXiv  Detail & Related papers  (2026-02-03T00:54:32Z)
• RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression [25.190765258589707]
  We present RocketKV, a training-free KV cache compression strategy containing two consecutive stages.<n>In the first stage, it performs coarse-grain permanent KV cache eviction on the input sequence tokens.<n>In the second stage, it adopts a hybrid sparse attention method to conduct fine-grain top-k sparse attention.
  arXiv  Detail & Related papers  (2025-02-19T19:12:46Z)
• ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference [61.412894960600205]
  Large Language Models (LLMs) require significant GPU memory when processing long texts.<n>ChunkKV reimagines KV cache compression by treating semantic chunks as basic compression units.<n>Result: ChunkKV outperforms state-of-the-art methods by up to 8.7% in precision.
  arXiv  Detail & Related papers  (2025-02-01T03:49:47Z)
• KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing [58.29726147780976]
  We propose a plug-and-play method called textit KVSharer, which shares the KV cache between layers to achieve layer-wise compression. Experiments show that textit KVSharer can reduce KV cache computation by 30%, thereby lowering memory consumption. We verify that textit KVSharer is compatible with existing intra-layer KV cache compression methods, and combining both can further save memory.
  arXiv  Detail & Related papers  (2024-10-24T08:06:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.