Cover Image

LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yan, Feihong, Wei, Qingyan, Tang, Jiayi, Li, Jiajun, Wang, Yulin, Hu, Xuming, Li, Huiqi, Zhang, Linfeng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling
by: Yan, Feihong, et al.
Published: (2025)

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

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

Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching
by: Zou, Chang, et al.
Published: (2024)

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free
by: Zhang, Evelyn, et al.
Published: (2024)

Efficient Sparse-to-Dense Visual Localization via Compact Gaussian Scene Representation and Accelerated Dense Pose Estimation
by: Li, Zizhuo, et al.
Published: (2026)

CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
by: Li, Zian, et al.
Published: (2025)

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

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
by: Liu, Jiacheng, et al.
Published: (2025)

Accelerating Diffusion Transformers with Token-wise Feature Caching
by: Zou, Chang, et al.
Published: (2024)

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

DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature Caching
by: Zou, Chang, et al.
Published: (2026)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
by: Zheng, Zhixin, et al.
Published: (2025)

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

WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
by: Feng, Weilun, et al.
Published: (2026)

ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration
by: Cao, Fanpu, et al.
Published: (2025)

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning
by: Guo, Hang, et al.
Published: (2025)

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
by: Wang, Jiangshan, et al.
Published: (2026)

FreqCa: Accelerating Diffusion Models via Frequency-Aware Caching
by: Liu, Jiacheng, et al.
Published: (2025)

DSPFusion: Image Fusion via Degradation and Semantic Dual-Prior Guidance
by: Tang, Linfeng, et al.
Published: (2025)

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

No Cache Left Idle: Accelerating diffusion model via Extreme-slimming Caching
by: Wen, Tingyan, et al.
Published: (2025)

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

Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers
by: Chen, Guantao, et al.
Published: (2026)

StreamMeCo: Long-Term Agent Memory Compression for Efficient Streaming Video Understanding
by: Wang, Junxi, et al.
Published: (2026)

Controllable Skin Synthesis via Lesion-Focused Vector Autoregression Model
by: Sun, Jiajun, et al.
Published: (2025)

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

Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
by: Luo, Jiayi, et al.
Published: (2026)

Token Caching for Diffusion Transformer Acceleration
by: Lou, Jinming, et al.
Published: (2024)

Let Features Decide Their Own Solvers: Hybrid Feature Caching for Diffusion Transformers
by: Zheng, Shikang, et al.
Published: (2025)

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

Relational Feature Caching for Accelerating Diffusion Transformers
by: Son, Byunggwan, et al.
Published: (2026)

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

CacheQuant: Comprehensively Accelerated Diffusion Models
by: Liu, Xuewen, et al.
Published: (2025)

HiCache: A Plug-in Scaled-Hermite Upgrade for Taylor-Style Cache-then-Forecast Diffusion Acceleration
by: Feng, Liang, et al.
Published: (2025)

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

Accelerating Controllable Generation via Hybrid-grained Cache
by: Liu, Lin, et al.
Published: (2025)

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

Accelerating Rectified Flow Models via Trajectory-Aware Caching
by: Liu, Xiao, et al.
Published: (2026)

SenCache: Accelerating Diffusion Model Inference via Sensitivity-Aware Caching
by: Haghighi, Yasaman, et al.
Published: (2026)