Imagen de Portada

Pathwise Test-Time Correction for Autoregressive Long Video Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xiang, Xunzhi, Duan, Zixuan, Zhang, Guiyu, Zhang, Haiyu, Gao, Zhe, Wu, Junta, Zhang, Shaofeng, Wang, Tengfei, Fan, Qi, Guo, Chunchao
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation
por: Xiang, Xunzhi, et al.
Publicado: (2025)

Make It Efficient: Dynamic Sparse Attention for Autoregressive Image Generation
por: Xiang, Xunzhi, et al.
Publicado: (2025)

WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
por: Sun, Wenqiang, et al.
Publicado: (2025)

Denoising Vision Transformer Autoencoder with Spectral Self-Regularization
por: Xiang, Xunzhi, et al.
Publicado: (2025)

WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories
por: Zhang, Yisu, et al.
Publicado: (2026)

SymphoMotion: Joint Control of Camera Motion and Object Dynamics for Coherent Video Generation
por: Zhang, Guiyu, et al.
Publicado: (2026)

WorldCompass: Reinforcement Learning for Long-Horizon World Models
por: Wang, Zehan, et al.
Publicado: (2026)

Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
por: Zhang, Guiyu, et al.
Publicado: (2025)

Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
por: Huang, Tianyu, et al.
Publicado: (2025)

Agents on a Tree: Pathwise Coordination for Multi-Objective Molecular Optimization
por: Zhang, Jia, et al.
Publicado: (2026)

WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
por: Liu, Yifan, et al.
Publicado: (2025)

Selective, Regularized, and Calibrated: Harnessing Vision Foundation Models for Cross-Domain Few-Shot Semantic Segmentation
por: Ma, Junyuan, et al.
Publicado: (2026)

FlashWorld: High-quality 3D Scene Generation within Seconds
por: Li, Xinyang, et al.
Publicado: (2025)

DreamWorld: Unified World Modeling in Video Generation
por: Tan, Boming, et al.
Publicado: (2026)

Video-T1: Test-Time Scaling for Video Generation
por: Liu, Fangfu, et al.
Publicado: (2025)

SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation
por: Tan, Shanwen, et al.
Publicado: (2026)

MoCA: Mixture-of-Components Attention for Scalable Compositional 3D Generation
por: Li, Zhiqi, et al.
Publicado: (2025)

Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity
por: Tian, Jiahao, et al.
Publicado: (2026)

VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory
por: Yu, Yifei, et al.
Publicado: (2025)

Speculative Decoding for Autoregressive Video Generation
por: Hu, Yuezhou, et al.
Publicado: (2026)

Context Forcing: Consistent Autoregressive Video Generation with Long Context
por: Chen, Shuo, et al.
Publicado: (2026)

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
por: Ye, Bo, et al.
Publicado: (2026)

Repurposing 3D Generative Model for Autoregressive Layout Generation
por: Feng, Haoran, et al.
Publicado: (2026)

SpriteHand: Real-Time Versatile Hand-Object Interaction with Autoregressive Video Generation
por: Li, Zisu, et al.
Publicado: (2025)

Automated Metaheuristic Algorithm Design with Autoregressive Learning
por: Zhao, Qi, et al.
Publicado: (2024)

MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation
por: Yang, Dingdong, et al.
Publicado: (2026)

TokenTrim: Inference-Time Token Pruning for Autoregressive Long Video Generation
por: Shaulov, Ariel, et al.
Publicado: (2026)

LIVE: Long-horizon Interactive Video World Modeling
por: Huang, Junchao, et al.
Publicado: (2026)

Convergence Guarantees for RMSProp and Adam in Generalized-smooth Non-convex Optimization with Affine Noise Variance
por: Zhang, Qi, et al.
Publicado: (2024)

Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
por: Cheng, Tianle, et al.
Publicado: (2025)

Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video Generation
por: Han, Yizhao, et al.
Publicado: (2026)

Continuous Speculative Decoding for Autoregressive Image Generation
por: Wang, Zili, et al.
Publicado: (2024)

Hypothesize-Then-Verify: Speculative Root Cause Analysis for Microservices with Pathwise Parallelism
por: Zhang, Lingzhe, et al.
Publicado: (2026)

R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
por: Wu, Zijie, et al.
Publicado: (2026)

HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation
por: Zhang, Conglang, et al.
Publicado: (2026)

Infinite Gaze Generation for Videos with Autoregressive Diffusion
por: Kang, Jenna, et al.
Publicado: (2026)

ARLON: Boosting Diffusion Transformers with Autoregressive Models for Long Video Generation
por: Li, Zongyi, et al.
Publicado: (2024)

Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
por: Liu, Kunhao, et al.
Publicado: (2025)

Geometry-Aware Implicit Memory for Video World Models
por: Wei, Zhengxuan, et al.
Publicado: (2026)

Taming Teacher Forcing for Masked Autoregressive Video Generation
por: Zhou, Deyu, et al.
Publicado: (2025)