Copertina

DDiT: Dynamic Patch Scheduling for Efficient Diffusion Transformers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kim, Dahye, Ghadiyaram, Deepti, Gadde, Raghudeep
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations
di: Kim, Dahye, et al.
Pubblicazione: (2025)

$\textit{Revelio}$: Interpreting and leveraging semantic information in diffusion models
di: Kim, Dahye, et al.
Pubblicazione: (2024)

Swift Sampling: Selecting Temporal Surprises via Taylor Series
di: Kim, Dahye, et al.
Pubblicazione: (2026)

Improving Physical Object State Representation in Text-to-Image Generative Systems
di: Chen, Tianle, et al.
Pubblicazione: (2025)

FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
di: Lim, Youngsun, et al.
Pubblicazione: (2026)

Progressive Prompt Detailing for Improved Alignment in Text-to-Image Generative Models
di: Saichandran, Ketan Suhaas, et al.
Pubblicazione: (2025)

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

What's in a Latent? Leveraging Diffusion Latent Space for Domain Generalization
di: Thomas, Xavier, et al.
Pubblicazione: (2025)

Disentanglement in T-space for Faster and Distributed Training of Diffusion Models with Fewer Latent-states
di: Gupta, Samarth, et al.
Pubblicazione: (2025)

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning
di: Chen, Tianle, et al.
Pubblicazione: (2026)

Diffusion Model Patching via Mixture-of-Prompts
di: Ham, Seokil, et al.
Pubblicazione: (2024)

DDiT: Dynamic Resource Allocation for Diffusion Transformer Model Serving
di: Huang, Heyang, et al.
Pubblicazione: (2025)

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference
di: Fang, Jiarui, et al.
Pubblicazione: (2024)

FlowFixer: Towards Detail-Preserving Subject-Driven Generation
di: Jun, Jinyoung, et al.
Pubblicazione: (2026)

Improved Noise Schedule for Diffusion Training
di: Hang, Tiankai, et al.
Pubblicazione: (2024)

Improved Ear Verification with Vision Transformers and Overlapping Patches
di: Arun, Deeksha, et al.
Pubblicazione: (2025)

A Contrastive Learning Scheme with Transformer Innate Patches
di: Jyhne, Sander Riisøen, et al.
Pubblicazione: (2023)

PatchTraj: Unified Time-Frequency Representation Learning via Dynamic Patches for Trajectory Prediction
di: Liu, Yanghong, et al.
Pubblicazione: (2025)

VMonarch: Efficient Video Diffusion Transformers with Structured Attention
di: Liang, Cheng, et al.
Pubblicazione: (2026)

OminiControl2: Efficient Conditioning for Diffusion Transformers
di: Tan, Zhenxiong, et al.
Pubblicazione: (2025)

Reflection Removal through Efficient Adaptation of Diffusion Transformers
di: Zakarin, Daniyar, et al.
Pubblicazione: (2025)

Entropy Guided Dynamic Patch Segmentation for Time Series Transformers
di: Abeywickrama, Sachith, et al.
Pubblicazione: (2025)

Preserving Old Memories in Vivid Detail: Human-Interactive Photo Restoration Framework
di: Back, Seung-Yeon, et al.
Pubblicazione: (2024)

Disentangling Visual Transformers: Patch-level Interpretability for Image Classification
di: Jeanneret, Guillaume, et al.
Pubblicazione: (2025)

Accelerating Vision Transformers with Adaptive Patch Sizes
di: Choudhury, Rohan, et al.
Pubblicazione: (2025)

Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
di: Qiu, Jason, et al.
Pubblicazione: (2026)

Patch Rebirth: Toward Fast and Transferable Model Inversion of Vision Transformers
di: Heo, Seongsoo, et al.
Pubblicazione: (2025)

LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers
di: Chowdhury, Md Abtahi Majeed, et al.
Pubblicazione: (2025)

Unsupervised Salient Patch Selection for Data-Efficient Reinforcement Learning
di: Jiang, Zhaohui, et al.
Pubblicazione: (2024)

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

HQ-DiT: Efficient Diffusion Transformer with FP4 Hybrid Quantization
di: Liu, Wenxuan, et al.
Pubblicazione: (2024)

EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
di: Chen, Xinwang, et al.
Pubblicazione: (2024)

Foreground-Aware Dataset Distillation via Dynamic Patch Selection
di: Li, Longzhen, et al.
Pubblicazione: (2026)

Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
di: Lee, Dong In, et al.
Pubblicazione: (2025)

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers
di: Shi, Minglei, et al.
Pubblicazione: (2025)

Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer
di: Kang, Sungmin, et al.
Pubblicazione: (2024)

EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation
di: Kodavanti, Sravanth, et al.
Pubblicazione: (2026)

Dynamic VLM-Guided Negative Prompting for Diffusion Models
di: Chang, Hoyeon, et al.
Pubblicazione: (2025)

Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
di: Cho, Hansam, et al.
Pubblicazione: (2025)

Diffusion-Driven Deceptive Patches: Adversarial Manipulation and Forensic Detection in Facial Identity Verification
di: Sayyafzadeh, Shahrzad, et al.
Pubblicazione: (2026)