In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion

arXiv:2609.32540 · cs.CV, cs.AI, cs.LG, cs.MM · Submitted 2026-09-26 · Read on arXiv

cs.CV, cs.AI, cs.LG, cs.MM

Submitted: 2026-09-26

Updated: 2026-09-30

Project page: https://yikai-wang.github.io/FlashForward

Terminology

• Distillation — 29× in this paper · explained in 2 episodes
• Diffusion Model — 14× in this paper · explained in 8 episodes
• Diffusion Models — 13× in this paper · explained in 6 episodes
• Ablation — 6× in this paper · explained in 1 episode
• KV cache — 6× in this paper · explained in 3 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Anchor Source — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• LoRA Adapters — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Flow Matching — 2× in this paper · explained in 8 episodes
• Generative Modeling — 2× in this paper · explained in 3 episodes
• Latent Diffusion Model — 2× in this paper · explained in 2 episodes
• Latent Diffusion Models — 2× in this paper · explained in 2 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• World Model — 2× in this paper · explained in 7 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Amortization — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Frozen model — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Sparse Attention — 1× in this paper · explained in 5 episodes

Sources

• Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• SkyReels-V2: Infinite-length Film Generative Model
• Long-Context Autoregressive Video Modeling with Next-Frame Prediction
• LTX-Video: Realtime Video Latent Diffusion
• Latent Video Diffusion Models for High-Fidelity Long Video Generation
• SneakPeek: Future-Guided Instructional Streaming Video Generation
• Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
• Ms. Forcing: Efficient Streaming Video Generation with Multi-Scale Patchification and Attention
• TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models
• Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
• MAGI-1: Autoregressive Video Generation at Scale
• Wan: Open and Advanced Large-Scale Video Generative Models
• Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation
• Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models