WorldAttention: An Efficient Attention Architecture for Interactive Video World Models

arXiv:2609.34606 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/alibaba-damo-academy/WorldAttention

Project page: https://alibaba-damo-academy.github.io/WorldAttention

Terminology

• KV cache — 48× in this paper · explained in 3 episodes
• Sparsity — 38× in this paper · explained in 4 episodes
• Sparse Attention — 36× in this paper · explained in 5 episodes
• Consistency — 24× in this paper · explained in 3 episodes
• Hybrid Sparse Attention — 11× in this paper
• Transformer — 9× in this paper · explained in 2 episodes
• Ablation — 8× in this paper · explained in 1 episode
• World Model — 7× in this paper · explained in 7 episodes
• Fidelity — 5× in this paper · explained in 2 episodes
• Adaptation — 4× in this paper · explained in 1 episode
• Core — 4× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Redundancy — 4× in this paper · explained in 2 episodes
• Robustness — 4× in this paper · explained in 5 episodes
• Ablation study — 3× in this paper · explained in 1 episode
• Cosine Similarity — 3× in this paper · explained in 3 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Attention Mechanism — 2× in this paper · explained in 3 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Computational overhead — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Sparse Linear Attention — 2× in this paper
• Temporal consistency — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Distillation — 1× in this paper · explained in 2 episodes
• Distribution Matching — 1× in this paper · explained in 2 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Latent Space — 1× in this paper · explained in 7 episodes
• Prompt Adherence — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Semantic Alignment — 1× in this paper · explained in 3 episodes
• Semantic Similarity — 1× in this paper · explained in 2 episodes
• Temporal Correlations — 1× in this paper · explained in 2 episodes
• Transformer Models — 1× in this paper · explained in 2 episodes
• Video Drift Error — 1× in this paper

Sources

• Qwen Technical Report
• Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
• Scaling Linear Attention with Sparse State Expansion
• Mixture of Contexts for Long Video Generation
• SkyReels-V2: Infinite-length Film Generative Model
• SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
• Autoregressive Video Generation without Vector Quantization
• StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation
• Long Context Tuning for Video Generation
• Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
• SEA: Sparse Linear Attention with Estimated Attention Mask
• FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
• Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
• Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
• Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
• MAGI-1: Autoregressive Video Generation at Scale
• Wan: Open and Advanced Large-Scale Video Generative Models
• Linformer: Self-Attention with Linear Complexity
• Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity
• RAM-Net: Linear-Time Sequence Modeling with Sparsely Addressable State

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