Imagen de Portada

Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yan, Feihong, Wang, Peiru, Zhu, Yao, Pang, Kaiyu, Wei, Qingyan, Li, Huiqi, Zhang, Linfeng
Formato:	Preprint
Publicado:	2025
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

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching
por: Yan, Feihong, et al.
Publicado: (2025)

ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
por: Yan, Feihong, et al.
Publicado: (2026)

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping
por: Li, Jiajun, et al.
Publicado: (2025)

Autoregressive Image Generation with Masked Bit Modeling
por: Yu, Qihang, et al.
Publicado: (2026)

Conditional Panoramic Image Generation via Masked Autoregressive Modeling
por: Wang, Chaoyang, et al.
Publicado: (2025)

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

LlamaSeg: Image Segmentation via Autoregressive Mask Generation
por: Deng, Jiru, et al.
Publicado: (2025)

OmniMotion: Multimodal Motion Generation with Continuous Masked Autoregression
por: Li, Zhe, et al.
Publicado: (2025)

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots
por: Zheng, Guangting, et al.
Publicado: (2025)

Masked Autoregressive Model for Weather Forecasting
por: Kim, Doyi, et al.
Publicado: (2024)

Not All Frames Deserve Full Computation: Accelerating Autoregressive Video Generation via Selective Computation and Predictive Extrapolation
por: Cui, Hanshuai, et al.
Publicado: (2026)

MMGT: Motion Mask Guided Two-Stage Network for Co-Speech Gesture Video Generation
por: Wang, Siyuan, et al.
Publicado: (2025)

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation
por: Wang, Lingfeng, et al.
Publicado: (2025)

Prompt-Guided Mask Proposal for Two-Stage Open-Vocabulary Segmentation
por: Li, Yu-Jhe, et al.
Publicado: (2024)

LaDiC: Are Diffusion Models Really Inferior to Autoregressive Counterparts for Image-to-Text Generation?
por: Wang, Yuchi, et al.
Publicado: (2024)

DREAM: Document Reconstruction via End-to-end Autoregressive Model
por: Li, Xin, et al.
Publicado: (2025)

VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
por: Liao, Xinyao, et al.
Publicado: (2026)

Accelerating Inference of Masked Image Generators via Reinforcement Learning
por: Subbaraman, Pranav, et al.
Publicado: (2025)

Layout-Conditioned Autoregressive Text-to-Image Generation via Structured Masking
por: Zheng, Zirui, et al.
Publicado: (2025)

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
por: Teng, Yao, et al.
Publicado: (2025)

Flow Matching Posterior Sampling: A Training-free Conditional Generation for Flow Matching
por: Song, Kaiyu, et al.
Publicado: (2024)

Accelerating Diffusion Models with One-to-Many Knowledge Distillation
por: Zhang, Linfeng, et al.
Publicado: (2024)

GenMask: Adapting DiT for Segmentation via Direct Mask Generation
por: Yang, Yuhuan, et al.
Publicado: (2026)

MARRS: Masked Autoregressive Unit-based Reaction Synthesis
por: Wang, Yabiao, et al.
Publicado: (2025)

Token Painter: Training-Free Text-Guided Image Inpainting via Mask Autoregressive Models
por: Jiang, Longtao, et al.
Publicado: (2025)

TokenAR: Multiple Subject Generation via Autoregressive Token-level enhancement
por: Sun, Haiyue, et al.
Publicado: (2025)

Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
por: Zhang, Yu, et al.
Publicado: (2026)

MV-CC: Mask Enhanced Video Model for Remote Sensing Change Caption
por: Liu, Ruixun, et al.
Publicado: (2024)

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer
por: Wu, Yecheng, et al.
Publicado: (2025)

SegEarth-R1: Geospatial Pixel Reasoning via Large Language Model
por: Li, Kaiyu, et al.
Publicado: (2025)

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

A Two-Stage Masked Autoencoder Based Network for Indoor Depth Completion
por: Sun, Kailai, et al.
Publicado: (2024)

MASC: Boosting Autoregressive Image Generation with a Manifold-Aligned Semantic Clustering
por: He, Lixuan, et al.
Publicado: (2025)

Accelerating Masked Image Generation by Learning Latent Controlled Dynamics
por: Zhu, Kaiwen, et al.
Publicado: (2026)

Efficient Autoregressive Shape Generation via Octree-Based Adaptive Tokenization
por: Deng, Kangle, et al.
Publicado: (2025)

Self-control: A Better Conditional Mechanism for Masked Autoregressive Model
por: Qu, Qiaoying, et al.
Publicado: (2024)

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis
por: Le, Thanh-Tung, et al.
Publicado: (2025)

MASC: Metal-Aware Sampling and Correction via Reinforcement Learning for Accelerated MRI
por: Lu, Zhengyi, et al.
Publicado: (2026)

F2HDR: Two-Stage HDR Video Reconstruction via Flow Adapter and Physical Motion Modeling
por: Yue, Huanjing, et al.
Publicado: (2026)

VarAD: Lightweight High-Resolution Image Anomaly Detection via Visual Autoregressive Modeling
por: Cao, Yunkang, et al.
Publicado: (2024)