Cover Image

Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Kunyang, Shah, Mubarak, Shang, Yuzhang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache
by: Li, Kunyang, et al.
Published: (2026)

EDiT: Efficient Diffusion Transformers with Linear Compressed Attention
by: Becker, Philipp, et al.
Published: (2025)

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

PTQ4DiT: Post-training Quantization for Diffusion Transformers
by: Wu, Junyi, et al.
Published: (2024)

ELSA: Exact Linear-Scan Attention for Fast and Memory-Light Vision Transformers
by: Hsu, Chih-Chung, et al.
Published: (2026)

Progressive Autoregressive Video Diffusion Models
by: Xie, Desai, et al.
Published: (2024)

GVD: Guiding Video Diffusion Model for Scalable Video Distillation
by: Li, Kunyang, et al.
Published: (2025)

Prompt Diffusion Robustifies Any-Modality Prompt Learning
by: Du, Yingjun, et al.
Published: (2024)

TIMED: Adversarial and Autoregressive Refinement of Diffusion-Based Time Series Generation
by: EskandariNasab, MohammadReza, et al.
Published: (2025)

Tracktention: Leveraging Point Tracking to Attend Videos Faster and Better
by: Lai, Zihang, et al.
Published: (2025)

BAgger: Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion Models
by: Po, Ryan, et al.
Published: (2025)

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
by: Yu, Sihyun, et al.
Published: (2024)

Reverse Stable Diffusion: What prompt was used to generate this image?
by: Croitoru, Florinel-Alin, et al.
Published: (2023)

Investigating the Effectiveness of Cross-Attention to Unlock Zero-Shot Editing of Text-to-Video Diffusion Models
by: Motamed, Saman, et al.
Published: (2024)

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention
by: Chen, Taiye, et al.
Published: (2025)

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing
by: Shi, Baifeng, et al.
Published: (2026)

Exploring Local Memorization in Diffusion Models via Bright Ending Attention
by: Chen, Chen, et al.
Published: (2024)

Diffusion Models in Vision: A Survey
by: Croitoru, Florinel-Alin, et al.
Published: (2022)

Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
by: Swinnen, Jonathan, et al.
Published: (2026)

Squeeze-and-Remember Block
by: Cakaj, Rinor, et al.
Published: (2024)

FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action Recognition
by: Dave, Ishan Rajendrakumar, et al.
Published: (2024)

Self-Distilled Masked Auto-Encoders are Efficient Video Anomaly Detectors
by: Ristea, Nicolae-Catalin, et al.
Published: (2023)

Attention Frequency Modulation: Training-Free Spectral Modulation of Diffusion Cross-Attention
by: Oh, Seunghun, et al.
Published: (2026)

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
by: Zhang, Jintao, et al.
Published: (2025)

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling
by: Yuan, Zhihang, et al.
Published: (2024)

DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture
by: Xiang, Qianlong, et al.
Published: (2024)

Sync from the Sea: Retrieving Alignable Videos from Large-Scale Datasets
by: Dave, Ishan Rajendrakumar, et al.
Published: (2024)

Reward-Forcing: Autoregressive Video Generation with Reward Feedback
by: Zhang, Jingran, et al.
Published: (2026)

Remembering Transformer for Continual Learning
by: Sun, Yuwei, et al.
Published: (2024)

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion
by: Huang, Xun, et al.
Published: (2025)

VGDFR: Diffusion-based Video Generation with Dynamic Latent Frame Rate
by: Yuan, Zhihang, et al.
Published: (2025)

BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
by: Wang, Fangyikang, et al.
Published: (2024)

LVSA: Training-Free Sparse Attention for Long Video Diffusion
by: Glorian, Gael, et al.
Published: (2026)

Test-Time Training with KV Binding Is Secretly Linear Attention
by: Liu, Junchen, et al.
Published: (2026)

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
by: Kwon, Taesung, et al.
Published: (2026)

Curriculum Direct Preference Optimization for Diffusion and Consistency Models
by: Croitoru, Florinel-Alin, et al.
Published: (2024)

CodaMal: Contrastive Domain Adaptation for Malaria Detection in Low-Cost Microscopes
by: Dave, Ishan Rajendrakumar, et al.
Published: (2024)

CLARITY: Medical World Model for Guiding Treatment Decisions by Modeling Context-Aware Disease Trajectories in Latent Space
by: Ding, Tianxingjian, et al.
Published: (2025)

Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models
by: Shen, Zhirong, et al.
Published: (2026)

Online Multi-spectral Neuron Tracing
by: Duan, Bin, et al.
Published: (2024)