# TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment arXiv: https://arxiv.org/abs/2606.13035 ยท HTML: https://mlsanity.com/paper/2606.13035/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Video generation, one of 14 directions in Diffusion models. - Builds on 35 of its 37 references that are in the map. - First posted on arXiv 11 Jun 2026. ## Placed in - Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/) ## Builds on (most cited first, 30 of 35) - [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023) - [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023) - [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023) - [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024) - [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024) - [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025) - [Sequence Level Training with Recurrent Neural Networks](https://mlsanity.com/paper/1511.06732/) (2015) - [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) - [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025) - [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025) - [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026) - [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025) - [WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling](https://mlsanity.com/paper/2512.14614/) (2025) - [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025) - [Long-Context Autoregressive Video Modeling with Next-Frame Prediction](https://mlsanity.com/paper/2503.19325/) (2025) - [Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout](https://mlsanity.com/paper/2511.20649/) (2025) - [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025) - [Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing](https://mlsanity.com/paper/2411.16375/) (2024) - [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025) - [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026) - [ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer](https://mlsanity.com/paper/2412.07720/) (2024) - [Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion](https://mlsanity.com/paper/2602.07775/) (2026) - [MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens](https://mlsanity.com/paper/2603.12513/) (2026) - [Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation](https://mlsanity.com/paper/2603.21366/) (2026) - [Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention](https://mlsanity.com/paper/2602.01801/) (2026) - [PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference](https://mlsanity.com/paper/2603.25730/) (2026) - [HiAR: Efficient Autoregressive Long Video Generation via Hierarchical Denoising](https://mlsanity.com/paper/2603.08703/) (2026) - [Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2605.09681/) (2026) - [Grounding World Simulation Models in a Real-World Metropolis](https://mlsanity.com/paper/2603.15583/) (2026) ## Built on by (most cited first, 8 of 8) - [Self Gradient Forcing: Native Long Video Extrapolation](https://mlsanity.com/paper/2607.20368/) (2026) - [RECAP-Forcing: Retaining Content Appearances for Long Video Generation](https://mlsanity.com/paper/2608.26671/) (2026) - [EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing](https://mlsanity.com/paper/2608.21424/) (2026) - [Vorch-Director: Interactive World Story Model via Noise-Aware Error Rectification](https://mlsanity.com/paper/2608.05776/) (2026) - [TaoMate: Anchor-Guided Memory Bridging Evolving and Reference States for Real-Time Audio-Video Digital Human Generation](https://mlsanity.com/paper/2607.24359/) (2026) - [Memorizon: Training World Models Beyond Their Context Window](https://mlsanity.com/paper/2610.00544/) (2026) - [Connected Self Forcing: Beyond Local Learning in Video Autoregression](https://mlsanity.com/paper/2610.12156/) (2026) - [FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation](https://mlsanity.com/paper/2610.14568/) (2026) ## Abstract (arXiv) Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content. However, extending these models to minute-level generation remains challenging: the limited KV-cache budget prevents the model from retaining the full history, while repeatedly conditioning on self-generated frames induces a context distribution shift that accumulates over time, leading to visual artifacts, quality degradation, and temporal drift. In this paper, we propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation. TetherCache organizes the cache into sink, memory, and recent regions, and introduces two complementary mechanisms. First, GRAB (Gated Recall with Attention-Diversity Balancing) selects long-range memory frames using a gated score that combines attention-based relevance with temporal diversity, preserving informative yet diverse historical context under a fixed cache budget. Second, TAME (Trusted Alignment via Memory Editing) lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution, reducing the pollution caused by drifted historical features. Built on Self-Forcing, TetherCache consistently improves long-video generation quality on VBench-Long across 30s, 60s, and 240s settings. In particular, for 240s generation, it substantially improves overall and semantic scores while reducing quality drift from 7.84 to 1.33, demonstrating its effectiveness for stable long-horizon autoregressive video diffusion.