Cover Image

Fast Autoregressive Video Diffusion and World Models with Temporal Cache Compression and Sparse Attention

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Samuel, Dvir, Tzachor, Issar, Levy, Matan, Green, Micahel, Chechik, Gal, Ben-Ari, Rami
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval
by: Tzachor, Issar, et al.
Published: (2026)

Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization
by: Green, Michael, et al.
Published: (2025)

OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
by: Samuel, Dvir, et al.
Published: (2025)

Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval
by: Samuel, Dvir, et al.
Published: (2024)

Retrieval-Augmented Gaussian Avatars: Improving Expression Generalization
by: Levy, Matan, et al.
Published: (2026)

Fast 4D Mesh Generation by Spatio-Temporal Attention Chains
by: Samuel, Dvir, et al.
Published: (2026)

EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition
by: Tzachor, Issar, et al.
Published: (2024)

Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
by: Samuel, Dvir, et al.
Published: (2023)

Task-Specific Adaptation with Restricted Model Access
by: Levy, Matan, et al.
Published: (2025)

Per-Query Visual Concept Learning
by: Malca, Ori, et al.
Published: (2025)

Set Features for Anomaly Detection
by: Cohen, Niv, et al.
Published: (2023)

Bringing Objects to Life: training-free 4D generation from 3D objects through view consistent noise
by: Rahamim, Ohad, et al.
Published: (2024)

Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
by: Tewel, Yoad, et al.
Published: (2024)

Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models
by: Ji, Yicheng, et al.
Published: (2026)

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
by: Lv, Chengtao, et al.
Published: (2026)

Story2Board: A Training-Free Approach for Expressive Storyboard Generation
by: Dinkevich, David, et al.
Published: (2025)

MSC: Multi-Scale Spatio-Temporal Causal Attention for Autoregressive Video Diffusion
by: Xu, Xunnong, et al.
Published: (2024)

Motion by Queries: Identity-Motion Trade-offs in Text-to-Video Generation
by: Atzmon, Yuval, et al.
Published: (2024)

Sparse Forcing: Native Trainable Sparse Attention for Real-time Autoregressive Diffusion Video Generation
by: Xu, Boxun, et al.
Published: (2026)

LiveSVG: Zero-Shot SVG Animation via Video Generation
by: Levy, Matan, et al.
Published: (2026)

CarGait: Cross-Attention based Re-ranking for Gait recognition
by: Habib, Gavriel, et al.
Published: (2025)

RL-RC-DoT: A Block-level RL agent for Task-Aware Video Compression
by: Gadot, Uri, et al.
Published: (2025)

Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment
by: Rassin, Royi, et al.
Published: (2023)

QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification
by: Feng, Weilun, et al.
Published: (2025)

Compositional Video Generation via Inference-Time Guidance
by: Shaulov, Ariel, et al.
Published: (2026)

Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion
by: Chen, Hanmo, et al.
Published: (2026)

FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
by: Luo, Xiangyang, et al.
Published: (2025)

From Slow Bidirectional to Fast Autoregressive Video Diffusion Models
by: Yin, Tianwei, et al.
Published: (2024)

VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
by: Yesiltepe, Hidir, et al.
Published: (2026)

Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling
by: Qin, Ziran, et al.
Published: (2025)

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
by: Gao, Kaifeng, et al.
Published: (2024)

JUST-DUB-IT: Video Dubbing via Joint Audio-Visual Diffusion
by: Chen, Anthony, et al.
Published: (2026)

LiteAttention: A Temporal Sparse Attention for Diffusion Transformers
by: Shmilovich, Dor, et al.
Published: (2025)

Data-Driven Loss Functions for Inference-Time Optimization in Text-to-Image
by: Yiflach, Sapir Esther, et al.
Published: (2025)

X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
by: Zeng, Yixiao, et al.
Published: (2026)

Single Image Iterative Subject-driven Generation and Editing
by: Shpitzer, Yair, et al.
Published: (2025)

Key-Locked Rank One Editing for Text-to-Image Personalization
by: Tewel, Yoad, et al.
Published: (2023)

Assessing Image Quality Using a Simple Generative Representation
by: Raviv, Simon, et al.
Published: (2024)

FastCache: Fast Caching for Diffusion Transformer Through Learnable Linear Approximation
by: Liu, Dong, et al.
Published: (2025)

MagCache: Fast Video Generation with Magnitude-Aware Cache
by: Ma, Zehong, et al.
Published: (2025)