Image de couverture de livre

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cui, Hanshuai, Tang, Zhiqing, Yao, Zhi, Meng, Fanshuai, Jia, Weijia, Zhao, Wei
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Semantic-Aware Caching for Efficient Image Generation in Edge Computing
par: Cui, Hanshuai, et autres
Publié: (2025)

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
par: Cui, Hanshuai, et autres
Publié: (2025)

Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers
par: Cui, Hanshuai, et autres
Publié: (2026)

LRScheduler: A Layer-aware and Resource-adaptive Container Scheduler in Edge Computing
par: Tang, Zhiqing, et autres
Publié: (2025)

Long-Context Autoregressive Video Modeling with Next-Frame Prediction
par: Gu, Yuchao, et autres
Publié: (2025)

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
par: Ye, Bo, et autres
Publié: (2026)

VELO: A Vector Database-Assisted Cloud-Edge Collaborative LLM QoS Optimization Framework
par: Yao, Zhi, et autres
Publié: (2024)

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction
par: Ji, Longbin, et autres
Publié: (2026)

Autoregressive Video Generation beyond Next Frames Prediction
par: Ren, Sucheng, et autres
Publié: (2025)

A Fast Task Offloading Optimization Framework for IRS-Assisted Multi-Access Edge Computing System
par: Wu, Jianqiu, et autres
Publié: (2023)

Low-Latency Layer-Aware Proactive and Passive Container Migration in Meta Computing
par: Liu, Mengjie, et autres
Publié: (2024)

Adaptive Configuration Selection for Multi-Model Inference Pipelines in Edge Computing
par: Sheng, Jinhao, et autres
Publié: (2025)

EAT: QoS-Aware Edge-Collaborative AIGC Task Scheduling via Attention-Guided Diffusion Reinforcement Learning
par: Xu, Zhifei, et autres
Publié: (2025)

Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
par: Ren, Shuhuai, et autres
Publié: (2025)

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping
par: Dong, Haotian, et autres
Publié: (2025)

RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
par: Lu, Yanzuo, et autres
Publié: (2026)

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep
par: Liu, Tianyi, et autres
Publié: (2026)

Autoregressive Neural Network Extrapolation of Quantum Spin Dynamics Across Time and Space
par: Pugzlys, Hubert, et autres
Publié: (2025)

TabularMath: Evaluating Computational Extrapolation in Tabular Learning via Program-Verified Synthesis
par: Cheng, Zerui, et autres
Publié: (2026)

Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling
par: Yan, Feihong, et autres
Publié: (2025)

Extrapolating Jet Radiation with Autoregressive Transformers
par: Butter, Anja, et autres
Publié: (2024)

High-Speed FHD Full-Color Video Computer-Generated Holography
par: Zhang, Haomiao, et autres
Publié: (2025)

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations
par: Li, Jinghan, et autres
Publié: (2025)

Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning
par: Wang, Xubin, et autres
Publié: (2026)

Focused Forcing: Content-Aware Per-Frame KV Selection for Efficient Autoregressive Video Diffusion
par: Cai, Peiliang, et autres
Publié: (2026)

Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models
par: Wang, Xubin, et autres
Publié: (2025)

Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
par: Wang, Yuan, et autres
Publié: (2026)

Accelerating Training of Autoregressive Video Generation Models via Local Optimization with Representation Continuity
par: Zhou, Yucheng, et autres
Publié: (2026)

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
par: Liao, Xinyao, et autres
Publié: (2026)

Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models
par: Zhang, Zheyu, et autres
Publié: (2025)

Pretraining Frame Preservation for Lightweight Autoregressive Video History Embedding
par: Zhang, Lvmin, et autres
Publié: (2025)

End-to-End Training for Autoregressive Video Diffusion via Self-Resampling
par: Guo, Yuwei, et autres
Publié: (2025)

Functional Accelerated Failure Time Models for Predicting Time Since Cannabis Use
par: Qian, Weijia, et autres
Publié: (2025)

Autoregressive Image Generation with Vision Full-view Prompt
par: Cai, Miaomiao, et autres
Publié: (2025)

Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment
par: Wang, Xubin, et autres
Publié: (2025)

Deserving the Option to Give
par: Jeffrey Moriarty
Publié: (2024)

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
par: Lei, Jiabao, et autres
Publié: (2025)

Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention
par: Lv, Chengtao, et autres
Publié: (2026)

Reward-Forcing: Autoregressive Video Generation with Reward Feedback
par: Zhang, Jingran, et autres
Publié: (2026)

All Individuals Deserve Support: Collaborating To Prevent HIV/AIDS among Homeless Youth.
par: Sherman, Nancy E.
Publié: (1998)