Imagen de Portada

Self-Adversarial One Step Generation via Condition Shifting

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Deyuan, Sun, Peng, Han, Yansen, Cheng, Zhenglin, Chen, Chuyan, Lin, Tao
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
por: Cheng, Zhenglin, et al.
Publicado: (2025)

GMem: A Modular Approach for Ultra-Efficient Generative Models
por: Tang, Yi, et al.
Publicado: (2024)

Phased One-Step Adversarial Equilibrium for Video Diffusion Models
por: Cheng, Jiaxiang, et al.
Publicado: (2025)

Towards One-step Causal Video Generation via Adversarial Self-Distillation
por: Yang, Yongqi, et al.
Publicado: (2025)

Adversarial Concept Distillation for One-Step Diffusion Personalization
por: Yang, Yixiong, et al.
Publicado: (2025)

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

DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
por: Sun, Xianbing, et al.
Publicado: (2026)

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
por: Selikhanovych, Daniil, et al.
Publicado: (2025)

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
por: Song, Yuda, et al.
Publicado: (2024)

SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
por: Lin, Yexiong, et al.
Publicado: (2026)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
por: Dao, Quan, et al.
Publicado: (2024)

Diffusion Adversarial Post-Training for One-Step Video Generation
por: Lin, Shanchuan, et al.
Publicado: (2025)

RESTORE: Towards Feature Shift for Vision-Language Prompt Learning
por: Yang, Yuncheng, et al.
Publicado: (2024)

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
por: Mammadov, Abbas, et al.
Publicado: (2026)

Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows
por: Wang, Zihan, et al.
Publicado: (2026)

Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning
por: Zuo, Yushen, et al.
Publicado: (2024)

OSDFace: One-Step Diffusion Model for Face Restoration
por: Wang, Jingkai, et al.
Publicado: (2024)

ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
por: Liu, Aoyu, et al.
Publicado: (2026)

Improving Adversarial Robustness via Decoupled Visual Representation Masking
por: Liu, Decheng, et al.
Publicado: (2024)

Sakuga-42M Dataset: Scaling Up Cartoon Research
por: Pan, Zhenglin
Publicado: (2024)

OneActor: Consistent Character Generation via Cluster-Conditioned Guidance
por: Wang, Jiahao, et al.
Publicado: (2024)

Diffusion Models Are Innate One-Step Generators
por: Zheng, Bowen, et al.
Publicado: (2024)

Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
por: Cheng, Zhiyuan, et al.
Publicado: (2024)

ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
por: Souček, Tomáš, et al.
Publicado: (2024)

Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach
por: Liu, Hangyu, et al.
Publicado: (2025)

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction
por: Hu, Tao, et al.
Publicado: (2025)

Will Pre-Training Ever End? A First Step Toward Next-Generation Foundation MLLMs via Self-Improving Systematic Cognition
por: Zhang, Xiaoying, et al.
Publicado: (2025)

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
por: Gong, Jue, et al.
Publicado: (2025)

Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation
por: Wang, Chuhan, et al.
Publicado: (2026)

Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes
por: Zhang, Chuyan, et al.
Publicado: (2025)

Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation
por: Tang, Yushun, et al.
Publicado: (2025)

One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration
por: Wang, Chaoyang, et al.
Publicado: (2026)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
por: Zhao, Chenxi, et al.
Publicado: (2026)

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
por: Liu, Yi, et al.
Publicado: (2025)

StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation
por: Pan, Zhenglin, et al.
Publicado: (2025)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
por: Luan, Wuyang, et al.
Publicado: (2026)

OSV: One Step is Enough for High-Quality Image to Video Generation
por: Mao, Xiaofeng, et al.
Publicado: (2024)

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
por: Lu, Hongbo, et al.
Publicado: (2026)

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
por: Sun, Peng, et al.
Publicado: (2026)

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
por: Lin, Jiang, et al.
Publicado: (2025)