Image de couverture de livre

Self-Adversarial One Step Generation via Condition Shifting

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Deyuan, Sun, Peng, Han, Yansen, Cheng, Zhenglin, Chen, Chuyan, Lin, Tao
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
par: Cheng, Zhenglin, et autres
Publié: (2025)

GMem: A Modular Approach for Ultra-Efficient Generative Models
par: Tang, Yi, et autres
Publié: (2024)

Phased One-Step Adversarial Equilibrium for Video Diffusion Models
par: Cheng, Jiaxiang, et autres
Publié: (2025)

Towards One-step Causal Video Generation via Adversarial Self-Distillation
par: Yang, Yongqi, et autres
Publié: (2025)

Adversarial Concept Distillation for One-Step Diffusion Personalization
par: Yang, Yixiong, et autres
Publié: (2025)

SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
par: Wang, Jianyi, et autres
Publié: (2025)

DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport
par: Sun, Xianbing, et autres
Publié: (2026)

One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillation
par: Selikhanovych, Daniil, et autres
Publié: (2025)

SDXS: Real-Time One-Step Latent Diffusion Models with Image Conditions
par: Song, Yuda, et autres
Publié: (2024)

SubFlow: Sub-mode Conditioned Flow Matching for Diverse One-Step Generation
par: Lin, Yexiong, et autres
Publié: (2026)

Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generation
par: Dao, Quan, et autres
Publié: (2024)

Diffusion Adversarial Post-Training for One-Step Video Generation
par: Lin, Shanchuan, et autres
Publié: (2025)

RESTORE: Towards Feature Shift for Vision-Language Prompt Learning
par: Yang, Yuncheng, et autres
Publié: (2024)

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation
par: Mammadov, Abbas, et autres
Publié: (2026)

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

Towards Multi-View Consistent Style Transfer with One-Step Diffusion via Vision Conditioning
par: Zuo, Yushen, et autres
Publié: (2024)

OSDFace: One-Step Diffusion Model for Face Restoration
par: Wang, Jingkai, et autres
Publié: (2024)

ExpoCM: Exposure-Aware One-Step Generative Single-Image HDR Reconstruction
par: Liu, Aoyu, et autres
Publié: (2026)

Improving Adversarial Robustness via Decoupled Visual Representation Masking
par: Liu, Decheng, et autres
Publié: (2024)

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

OneActor: Consistent Character Generation via Cluster-Conditioned Guidance
par: Wang, Jiahao, et autres
Publié: (2024)

Diffusion Models Are Innate One-Step Generators
par: Zheng, Bowen, et autres
Publié: (2024)

Self-supervised Adversarial Training of Monocular Depth Estimation against Physical-World Attacks
par: Cheng, Zhiyuan, et autres
Publié: (2024)

ShowHowTo: Generating Scene-Conditioned Step-by-Step Visual Instructions
par: Souček, Tomáš, et autres
Publié: (2024)

Rethinking Target Label Conditioning in Adversarial Attacks: A 2D Tensor-Guided Generative Approach
par: Liu, Hangyu, et autres
Publié: (2025)

GMODiff: One-Step Gain Map Refinement with Diffusion Priors for HDR Reconstruction
par: Hu, Tao, et autres
Publié: (2025)

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

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance
par: Gong, Jue, et autres
Publié: (2025)

Accelerating Diffusion Decoders via Multi-Scale Sampling and One-Step Distillation
par: Wang, Chuhan, et autres
Publié: (2026)

Beyond Low-Rank Tuning: Model Prior-Guided Rank Allocation for Effective Transfer in Low-Data and Large-Gap Regimes
par: Zhang, Chuyan, et autres
Publié: (2025)

Progressive Conditioned Scale-Shift Recalibration of Self-Attention for Online Test-time Adaptation
par: Tang, Yushun, et autres
Publié: (2025)

One-Step Distillation of Discrete Diffusion Image Generators via Fixed-Point Iteration
par: Wang, Chaoyang, et autres
Publié: (2026)

Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
par: Zhao, Chenxi, et autres
Publié: (2026)

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation
par: Liu, Yi, et autres
Publié: (2025)

StructInbet: Integrating Explicit Structural Guidance into Inbetween Frame Generation
par: Pan, Zhenglin, et autres
Publié: (2025)

SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation
par: Luan, Wuyang, et autres
Publié: (2026)

OSV: One Step is Enough for High-Quality Image to Video Generation
par: Mao, Xiaofeng, et autres
Publié: (2024)

VisionNVS: Self-Supervised Inpainting for Novel View Synthesis under the Virtual-Shift Paradigm
par: Lu, Hongbo, et autres
Publié: (2026)

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
par: Sun, Peng, et autres
Publié: (2026)

FreeControl: Efficient, Training-Free Structural Control via One-Step Attention Extraction
par: Lin, Jiang, et autres
Publié: (2025)