# Addressable Memory for Video World Models

arXiv: https://arxiv.org/abs/2608.07408 · HTML: https://mlsanity.com/paper/2608.07408/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Video-generation world models and simulators, one of 11 directions in World models.
- Builds on 104 of its 120 references that are in the map.
- First posted on arXiv 7 Aug 2026.

## Placed in

- World models / [Video-generation world models and simulators](https://mlsanity.com/wm/video-generation-world-models-and-simulators/)

## Builds on (most cited first, 30 of 104)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation](https://mlsanity.com/paper/2108.12409/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache](https://mlsanity.com/paper/2402.02750/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [YaRN: Efficient Context Window Extension of Large Language Models](https://mlsanity.com/paper/2309.00071/) (2023)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [The Impact of Positional Encoding on Length Generalization in Transformers](https://mlsanity.com/paper/2305.19466/) (2023)
- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Rotary Position Embedding for Vision Transformer](https://mlsanity.com/paper/2403.13298/) (2024)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [Memorizing Transformers](https://mlsanity.com/paper/2203.08913/) (2022)

## Built on by (most cited first, 15 of 15)

- [RECAP-Forcing: Retaining Content Appearances for Long Video Generation](https://mlsanity.com/paper/2608.26671/) (2026)
- [ConsistWorld: Evidence Routing for Consistent Multi-Agent World Models](https://mlsanity.com/paper/2609.22641/) (2026)
- [WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory](https://mlsanity.com/paper/2609.24984/) (2026)
- [OPIS: An Input-Grounded Benchmark for Multi-Object Memory in Video World Models](https://mlsanity.com/paper/2609.35052/) (2026)
- [Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models](https://mlsanity.com/paper/2609.35439/) (2026)
- [Honeycomb: Constant-Size Scene Memory Representation for Video World Models](https://mlsanity.com/paper/2609.37690/) (2026)
- [DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency](https://mlsanity.com/paper/2609.39096/) (2026)
- [LOCI: Spatial Linear Memory for Streaming World Models](https://mlsanity.com/paper/2609.40222/) (2026)
- [Memorizon: Training World Models Beyond Their Context Window](https://mlsanity.com/paper/2610.00544/) (2026)
- [Towards Automatic Video Annotation with ASH: Zero-Shot Open-Vocabulary Multi-Object Tracking and Segmentation](https://mlsanity.com/paper/2610.01022/) (2026)
- [MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation](https://mlsanity.com/paper/2610.02153/) (2026)
- [HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models](https://mlsanity.com/paper/2610.05739/) (2026)
- [GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models](https://mlsanity.com/paper/2610.13706/) (2026)
- [WorldMemBench: A Comprehensive Benchmark for Memory of Video World Models](https://mlsanity.com/paper/2610.19063/) (2026)
- [Into the LidarVerse: A Real-Time Unified LiDAR World Model Across Tasks and Sensors](https://mlsanity.com/paper/2610.19201/) (2026)

## Abstract (arXiv)

We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward previously generated frames. However, we find that models can no longer reliably address stored content once rollouts extend beyond the training horizon, because temporal Rotary Positional Embeddings (RoPE) offsets then fall outside the range seen during training and the model struggles to retrieve the relevant visual information through attention. Moreover, naively compressing the cache in the RoPE-rotated space corrupts memory by averaging together incompatible positional phases. To address this, we propose WorldTrace, a training-free memory framework for long-horizon visual persistence. WorldTrace keeps compressed memory addressable by assigning each summary slot a distinct, in-distribution virtual position. Within this addressable cache, we study two memory compression approaches: WorldTrace-Field compresses history for temporal coherence, while WorldTrace-Landmark stores verbatim scene traces at detected transitions for episodic recall. We further introduce LoopBench, a benchmark evaluating whether a compressed cache can reconstruct a previously visited scene after a long detour. WorldTrace-Field improves temporal consistency by +15.5%, and WorldTrace-Landmark improves episodic recall by +19.5% on LoopBench, extending visually persistent generation without retraining.