# Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation arXiv: https://arxiv.org/abs/2605.30083 ยท HTML: https://mlsanity.com/paper/2605.30083/ ## Key facts - Cited by 8 papers in the map (data through 14 Oct 2026). - Placed in Fast autoregressive visual generation, one of 12 directions in Efficient LLM inference and serving. - Builds on 39 of its 62 references that are in the map. - First posted on arXiv 28 May 2026. ## Placed in - Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/) ## Builds on (most cited first, 30 of 39) - [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025) - [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024) - [VideoGPT: Video Generation using VQ-VAE and Transformers](https://mlsanity.com/paper/2104.10157/) (2021) - [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024) - [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024) - [LTX-Video: Realtime Video Latent Diffusion](https://mlsanity.com/paper/2501.00103/) (2024) - [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025) - [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025) - [Autoregressive Video Generation without Vector Quantization](https://mlsanity.com/paper/2412.14169/) (2024) - [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026) - [Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model](https://mlsanity.com/paper/2502.10248/) (2025) - [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025) - [Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation](https://mlsanity.com/paper/2512.04678/) (2025) - [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025) - [Kling-Omni Technical Report](https://mlsanity.com/paper/2512.16776/) (2025) - [HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters](https://mlsanity.com/paper/2505.20156/) (2025) - [Progressive Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2410.08151/) (2024) - [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026) - [Context Forcing: Consistent Autoregressive Video Generation with Long Context](https://mlsanity.com/paper/2602.06028/) (2026) - [AR-Diffusion: Asynchronous Video Generation with Auto-Regressive Diffusion](https://mlsanity.com/paper/2503.07418/) (2025) - [VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory](https://mlsanity.com/paper/2512.04519/) (2025) - [Taming Teacher Forcing for Masked Autoregressive Video Generation](https://mlsanity.com/paper/2501.12389/) (2025) - [Pack and Force Your Memory: Long-form and Consistent Video Generation](https://mlsanity.com/paper/2510.01784/) (2025) - [Flow caching for autoregressive video generation](https://mlsanity.com/paper/2602.10825/) (2026) - [Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation](https://mlsanity.com/paper/2603.21366/) (2026) - [Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization](https://mlsanity.com/paper/2602.02958/) (2026) - [Efficient Autoregressive Video Diffusion with Dummy Head](https://mlsanity.com/paper/2601.20499/) (2026) - [VRoPE: Rotary Position Embedding for Video Large Language Models](https://mlsanity.com/paper/2502.11664/) (2025) - [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) ## Built on by (most cited first, 8 of 8) - [In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion](https://mlsanity.com/paper/2609.32540/) (2026) - [FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38839/) (2026) - [DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency](https://mlsanity.com/paper/2609.39096/) (2026) - [MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation](https://mlsanity.com/paper/2610.02153/) (2026) - [TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video Generation](https://mlsanity.com/paper/2610.02779/) (2026) - [ProAR: Learning Prospective Reasoning with Autoregressive Video Models](https://mlsanity.com/paper/2610.03664/) (2026) - [FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation](https://mlsanity.com/paper/2610.14568/) (2026) - [TempoKV: Predictive KV Cache Quantization for Autoregressive Video Generation](https://mlsanity.com/paper/2610.15324/) (2026) ## Abstract (arXiv) Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.