Cover Image

Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Cui, Hanshuai, Tang, Zhiqing, Ma, Qianli, Yao, Zhi, Jia, Weijia
Format:	Preprint
Published:	2026
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

BWCache: Accelerating Video Diffusion Transformers through Block-Wise Caching
by: Cui, Hanshuai, et al.
Published: (2025)

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

Forecast then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers
by: Zheng, Shikang, et al.
Published: (2025)

GM-Skip: Metric-Guided Transformer Block Skipping for Efficient Vision-Language Models
by: Huang, Lianming, et al.
Published: (2025)

Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
by: Chen, Guanjie, et al.
Published: (2024)

Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation
by: Cui, Mengmeng, 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)

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
by: Xie, Enze, et al.
Published: (2024)

SSI-DM: Singularity Skipping Inversion of Diffusion Models
by: Min, Chen, et al.
Published: (2026)

Consistent and Controllable Image Animation with Motion Linear Diffusion Transformers
by: Ma, Xin, et al.
Published: (2025)

SkipGS: Post-Densification Backward Skipping for Efficient 3DGS Training
by: Li, Jingxing, et al.
Published: (2026)

Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping
by: Park, Sunghyun, et al.
Published: (2026)

Skip-Vision: Efficient and Scalable Acceleration of Vision-Language Models via Adaptive Token Skipping
by: Zeng, Weili, et al.
Published: (2025)

Cyclical Temporal Encoding and Hybrid Deep Ensembles for Multistep Energy Forecasting
by: Khazem, Salim, et al.
Published: (2025)

Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
by: Hyung, Junha, et al.
Published: (2024)

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

Skip and Skip: Segmenting Medical Images with Prompts
by: Chen, Jiawei, et al.
Published: (2024)

Attention Surgery: An Efficient Recipe to Linearize Your Video Diffusion Transformer
by: Ghafoorian, Mohsen, et al.
Published: (2025)

UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths
by: Mao, Weijia, et al.
Published: (2025)

Efficient Diffusion as Low Light Enhancer
by: Lan, Guanzhou, et al.
Published: (2024)

Enhancing Feature Fusion of U-like Networks with Dynamic Skip Connections
by: Cao, Yue, et al.
Published: (2025)

Dynamic Differential Linear Attention: Enhancing Linear Diffusion Transformer for High-Quality Image Generation
by: Cao, Boyuan, et al.
Published: (2026)

Data-Efficient Ensemble Weather Forecasting with Diffusion Models
by: Valencia, Kevin, et al.
Published: (2025)

Semantic-Aware Caching for Efficient Image Generation in Edge Computing
by: Cui, Hanshuai, et al.
Published: (2025)

Multistep Consistency Models
by: Heek, Jonathan, et al.
Published: (2024)

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
by: He, Yefei, et al.
Published: (2023)

ProSMA-UNet: Decoder Conditioning for Proximal-Sparse Skip Feature Selection
by: Cheng, Chun-Wun, et al.
Published: (2026)

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

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
by: Chang, Shuning, et al.
Published: (2024)

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
by: Zhu, Haoyi, et al.
Published: (2026)

Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
by: Ravishankar, Advaith, et al.
Published: (2026)

Soft Masked Transformer for Point Cloud Processing with Skip Attention-Based Upsampling
by: He, Yong, et al.
Published: (2024)

LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
by: Wang, Jiahao, et al.
Published: (2025)

Stitch-a-Demo: Video Demonstrations from Multistep Descriptions
by: Wu, Chi Hsuan, et al.
Published: (2025)

Pretrained Diffusion Models Are Inherently Skipped-Step Samplers
by: Xu, Wenju
Published: (2025)

Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR
by: Yuan, Ziye, et al.
Published: (2026)

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
by: Fang, Tongcheng, et al.
Published: (2026)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
by: Xie, Enze, et al.
Published: (2025)

FBSDiff++: Improved Frequency Band Substitution of Diffusion Features for Efficient and Highly Controllable Text-Driven Image-to-Image Translation
by: Gao, Xiang, et al.
Published: (2026)

SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
by: Chen, Junsong, et al.
Published: (2025)