Cover Image

SoftCap: Soft-Budget Control for Diffusion Transformer Acceleration

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Yuhang, Qiu, Junxiang, Ben, Huixia, Tang, Zhenhua, Wang, Shuo, Hao, Yanbin
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

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

Accelerating Diffusion Transformer via Gradient-Optimized Cache
by: Qiu, Junxiang, et al.
Published: (2025)

Accelerating Diffusion Transformer via Error-Optimized Cache
by: Qiu, Junxiang, et al.
Published: (2025)

Hierarchical Space-Time Attention for Micro-Expression Recognition
by: Hao, Haihong, et al.
Published: (2024)

Soft Masked Mamba Diffusion Model for CT to MRI Conversion
by: Wang, Zhenbin, et al.
Published: (2024)

Model Inversion Attacks Through Target-Specific Conditional Diffusion Models
by: Li, Ouxiang, et al.
Published: (2024)

Progressive Text-to-Image Diffusion with Soft Latent Direction
by: Ye, YuTeng, et al.
Published: (2023)

StgcDiff: Spatial-Temporal Graph Condition Diffusion for Sign Language Transition Generation
by: He, Jiashu, et al.
Published: (2025)

SoftShadow: Leveraging Soft Masks for Penumbra-Aware Shadow Removal
by: Wang, Xinrui, et al.
Published: (2024)

SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition
by: Lei, Mengqi, et al.
Published: (2025)

RAPID^3: Tri-Level Reinforced Acceleration Policies for Diffusion Transformer
by: Zhao, Wangbo, et al.
Published: (2025)

SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding
by: Sheng, Yuan, et al.
Published: (2025)

Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentation
by: Wei, Binbin, et al.
Published: (2025)

Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
by: Zhu, Xingyu, et al.
Published: (2024)

HGFormer: Topology-Aware Vision Transformer with HyperGraph Learning
by: Wang, Hao, et al.
Published: (2025)

One Model, Many Budgets: Elastic Latent Interfaces for Diffusion Transformers
by: Haji-Ali, Moayed, et al.
Published: (2026)

Rethinking Visual Content Refinement in Low-Shot CLIP Adaptation
by: Lu, Jinda, et al.
Published: (2024)

Soft Prompt Generation for Domain Generalization
by: Bai, Shuanghao, et al.
Published: (2024)

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

Soft Augmentation for Image Classification
by: Liu, Yang, et al.
Published: (2022)

Soft Tail-dropping for Adaptive Visual Tokenization
by: Chen, Zeyuan, et al.
Published: (2026)

Token Transforming: A Unified and Training-Free Token Compression Framework for Vision Transformer Acceleration
by: Zeng, Fanhu, et al.
Published: (2025)

Interpretable Multimodal Out-of-context Detection with Soft Logic Regularization
by: Ma, Huanhuan, et al.
Published: (2024)

NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer
by: Liu, Shanyuan, et al.
Published: (2025)

Tunable Soft Equivariance with Guarantees
by: Rahman, Md Ashiqur, et al.
Published: (2026)

Boosting Few-Shot Learning via Attentive Feature Regularization
by: Zhu, Xingyu, et al.
Published: (2024)

STAvatar: Soft Binding and Temporal Density Control for Monocular 3D Head Avatars Reconstruction
by: Zhao, Jiankuo, et al.
Published: (2025)

S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
by: Lin, Weihao, et al.
Published: (2024)

Selective Vision-Language Subspace Projection for Few-shot CLIP
by: Zhu, Xingyu, et al.
Published: (2024)

ControlCap: Controllable Region-level Captioning
by: Zhao, Yuzhong, et al.
Published: (2024)

SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models
by: Li, Ouxiang, et al.
Published: (2025)

EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
by: Zhang, Yuxuan, et al.
Published: (2025)

Soft Self-labeling and Potts Relaxations for Weakly-Supervised Segmentation
by: Zhang, Zhongwen, et al.
Published: (2025)

Let Synthetic Data Shine: Domain Reassembly and Soft-Fusion for Single Domain Generalization
by: Li, Hao, et al.
Published: (2025)

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
by: Li, Yangming, et al.
Published: (2023)

DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity
by: Zhu, Haowei, et al.
Published: (2026)

Selective Volume Mixup for Video Action Recognition
by: Tan, Yi, et al.
Published: (2023)

ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing
by: Xing, Long, et al.
Published: (2025)

SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
by: Wang, Chengjie, et al.
Published: (2024)

UniSER: A Foundation Model for Unified Soft Effects Removal
by: Zhang, Jingdong, et al.
Published: (2025)