Copertina

SARA: Structural and Adversarial Representation Alignment for Training-efficient Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Hesen, Wang, Junyan, Tan, Zhiyu, Li, Hao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Raccoon: Multi-stage Diffusion Training with Coarse-to-Fine Curating Videos
di: Tan, Zhiyu, et al.
Pubblicazione: (2025)

DiverseDiT: Towards Diverse Representation Learning in Diffusion Transformers
di: Yang, Mengping, et al.
Pubblicazione: (2026)

E2ED^2:Direct Mapping from Noise to Data for Enhanced Diffusion Models
di: Tan, Zhiyu, et al.
Pubblicazione: (2024)

SARA: Semantically Adaptive Relational Alignment for Video Diffusion Models
di: Lian, Jiesong, et al.
Pubblicazione: (2026)

LiFT: Leveraging Human Feedback for Text-to-Video Model Alignment
di: Wang, Yibin, et al.
Pubblicazione: (2024)

Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing
di: Yang, Hao, et al.
Pubblicazione: (2026)

Unraveling MMDiT Blocks: Training-free Analysis and Enhancement of Text-conditioned Diffusion
di: Li, Binglei, et al.
Pubblicazione: (2026)

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment
di: Jiang, Kaixun, et al.
Pubblicazione: (2025)

ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack
di: Gao, Ziyi, et al.
Pubblicazione: (2024)

Towards Effective Usage of Human-Centric Priors in Diffusion Models for Text-based Human Image Generation
di: Wang, Junyan, et al.
Pubblicazione: (2024)

SARA: Controllable Makeup Transfer with Spatial Alignment and Region-Adaptive Normalization
di: Zhong, Xiaojing, et al.
Pubblicazione: (2023)

Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Training
di: Wang, Yanyun, et al.
Pubblicazione: (2026)

SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
di: Wang, Mengmeng, et al.
Pubblicazione: (2026)

Beyond Point-Wise Matching: Structural Representation Alignment for Accelerating Diffusion Transformers
di: Xu, Shaodong, et al.
Pubblicazione: (2026)

ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models
di: Kong, Fei, et al.
Pubblicazione: (2023)

Training-Free Representation Guidance for Diffusion Models with a Representation Alignment Projector
di: Zu, Wenqiang, et al.
Pubblicazione: (2026)

Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption
di: Qin, Luozheng, et al.
Pubblicazione: (2025)

Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
di: Zhang, Angang, et al.
Pubblicazione: (2025)

Structure-Guided Adversarial Training of Diffusion Models
di: Yang, Ling, et al.
Pubblicazione: (2024)

An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation
di: Tan, Zhiyu, et al.
Pubblicazione: (2024)

SARA: Scene-Aware Reconstruction Accelerator
di: Lee, Jee Won, et al.
Pubblicazione: (2026)

Fixed-Length Dense Fingerprint Representation with Alignment and Robust Enhancement
di: Pan, Zhiyu, et al.
Pubblicazione: (2025)

Boosting Latent Diffusion Models via Disentangled Representation Alignment
di: Page, John, et al.
Pubblicazione: (2026)

SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning
di: Ye, Xi, et al.
Pubblicazione: (2026)

What is Adversarial Training for Diffusion Models?
di: Rosaria, Briglia Maria, et al.
Pubblicazione: (2025)

CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
di: Peng, Sen, et al.
Pubblicazione: (2025)

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
di: Wang, Jianyi, et al.
Pubblicazione: (2025)

Boosting Adversarial Transferability with Spatial Adversarial Alignment
di: Chen, Zhaoyu, et al.
Pubblicazione: (2025)

MoAlign: Motion-Centric Representation Alignment for Video Diffusion Models
di: Bhowmik, Aritra, et al.
Pubblicazione: (2025)

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models
di: Hwang, Sungwon, et al.
Pubblicazione: (2025)

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
di: Liu, Xuewen, et al.
Pubblicazione: (2024)

Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion Models
di: Hou, Jinhui, et al.
Pubblicazione: (2026)

HEART: Hyperspherical Embedding Alignment via Kent-Representation Traversal in Diffusion Models
di: Roy, Arani, et al.
Pubblicazione: (2026)

Representation Learning and Identity Adversarial Training for Facial Behavior Understanding
di: Ning, Mang, et al.
Pubblicazione: (2024)

VidGen-1M: A Large-Scale Dataset for Text-to-video Generation
di: Tan, Zhiyu, et al.
Pubblicazione: (2024)

Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
di: Yu, Sihyun, et al.
Pubblicazione: (2024)

Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment
di: Fei, Hao, et al.
Pubblicazione: (2024)

NeRV-Diffusion: Diffuse Implicit Neural Representations for Video Synthesis
di: Ren, Yixuan, et al.
Pubblicazione: (2025)

Revisiting Adversarial Training at Scale
di: Wang, Zeyu, et al.
Pubblicazione: (2024)

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection
di: Tan, Xiaofeng, et al.
Pubblicazione: (2024)