# MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens

arXiv: https://arxiv.org/abs/2603.12513 · HTML: https://mlsanity.com/paper/2603.12513/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 62 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 30 of 54)

- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Extending Context Window of Large Language Models via Positional Interpolation](https://mlsanity.com/paper/2306.15595/) (2023)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [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)
- [VideoPoet: A Large Language Model for Zero-Shot Video Generation](https://mlsanity.com/paper/2312.14125/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [MAGVIT: Masked Generative Video Transformer](https://mlsanity.com/paper/2212.05199/) (2022)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)

## Built on by (most cited first, 27 of 27)

- [LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation](https://mlsanity.com/paper/2605.18739/) (2026)
- [Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models](https://mlsanity.com/paper/2606.25473/) (2026)
- [LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation](https://mlsanity.com/paper/2606.02553/) (2026)
- [ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU](https://mlsanity.com/paper/2607.19191/) (2026)
- [Addressable Memory for Video World Models](https://mlsanity.com/paper/2608.07408/) (2026)
- [Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation](https://mlsanity.com/paper/2605.16003/) (2026)
- [Echo-Infinity: Learning Evolving Memory for Real-Time Infinite Video Generation](https://mlsanity.com/paper/2606.04527/) (2026)
- [TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment](https://mlsanity.com/paper/2606.13035/) (2026)
- [FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion](https://mlsanity.com/paper/2606.10671/) (2026)
- [VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion](https://mlsanity.com/paper/2605.30351/) (2026)
- [Pyramid Forcing: Head-Aware Pyramid KV Cache Policy for High-Quality Long Video Generation](https://mlsanity.com/paper/2605.13111/) (2026)
- [MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold](https://mlsanity.com/paper/2606.13376/) (2026)
- [Vidu S1: A Real-Time Interactive Video Generation Model](https://mlsanity.com/paper/2607.03118/) (2026)
- [R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models](https://mlsanity.com/paper/2608.27328/) (2026)
- [AdaState: Self-Evolving Anchors for Streaming Video Generation](https://mlsanity.com/paper/2605.30349/) (2026)
- [RECAP-Forcing: Retaining Content Appearances for Long Video Generation](https://mlsanity.com/paper/2608.26671/) (2026)
- [Closing the Loop: Training-Free Revisit Consistency for Autoregressive Generative Rendering](https://mlsanity.com/paper/2607.21848/) (2026)
- [Tether the Subject, Release the Scene: Query-Aware Memory Routing for Long-Horizon Autoregressive Video Generation](https://mlsanity.com/paper/2608.26902/) (2026)
- [Compress to Remember: Learning Compact Memory via On-Policy Distillation for Long Video Generation](https://mlsanity.com/paper/2609.36364/) (2026)
- [Honeycomb: Constant-Size Scene Memory Representation for Video World Models](https://mlsanity.com/paper/2609.37690/) (2026)
- [LongTake: Learning to Sustain Dynamics in Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38562/) (2026)
- [Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation](https://mlsanity.com/paper/2610.02914/) (2026)
- [In-Distribution Forcing for Long Video Generation at Test Time](https://mlsanity.com/paper/2610.03120/) (2026)
- [SGF+: Decoupling Gradient Flows for Autoregressive Video Generation](https://mlsanity.com/paper/2610.10429/) (2026)
- [FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation](https://mlsanity.com/paper/2610.14568/) (2026)
- [World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models](https://mlsanity.com/paper/2610.17434/) (2026)
- [LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout](https://mlsanity.com/paper/2610.18289/) (2026)

## Abstract (arXiv)

Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagnation over long horizons. Current approaches preserve a fixed set of early tokens as attention sinks, but this static anchor cannot reflect the evolving content of a growing video. We introduce MemRoPE, a training-free framework with two co-designed components. Memory Tokens continuously compress all past keys into dual long-term and short-term streams via exponential moving averages, maintaining both global identity and recent dynamics within a fixed-size cache. Online RoPE Indexing caches unrotated keys and applies positional embeddings dynamically at attention time, ensuring the aggregation is free of conflicting positional phases. These two mechanisms are mutually enabling: positional decoupling makes temporal aggregation well-defined, while aggregation makes fixed-size caching viable for unbounded generation. Extensive experiments validate that MemRoPE outperforms existing methods in temporal coherence, visual fidelity, and subject consistency across minute- to hour-scale generation.