Imagen de Portada

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cheng, Zhenglin, Sun, Peng, Li, Jianguo, Lin, Tao
Formato:	Preprint
Publicado:	2025
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

Self-Adversarial One Step Generation via Condition Shifting
por: Liu, Deyuan, et al.
Publicado: (2026)

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

Mean Flows for One-step Generative Modeling
por: Geng, Zhengyang, et al.
Publicado: (2025)

One-step Latent-free Image Generation with Pixel Mean Flows
por: Lu, Yiyang, et al.
Publicado: (2026)

On the Design of One-step Diffusion via Shortcutting Flow Paths
por: Lin, Haitao, et al.
Publicado: (2025)

Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
por: Liu, Enshu, et al.
Publicado: (2024)

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

Point-MF: One-step Point Cloud Generation from a Single Image via Mean Flows
por: Baba, Yuta, et al.
Publicado: (2026)

FlowInOne:Unifying Multimodal Generation as Image-in, Image-out Flow Matching
por: Yi, Junchao, et al.
Publicado: (2026)

PixelFlow: Pixel-Space Generative Models with Flow
por: Chen, Shoufa, et al.
Publicado: (2025)

SoFlow: Solution Flow Models for One-Step Generative Modeling
por: Luo, Tianze, et al.
Publicado: (2025)

SplatFlow: Self-Supervised Dynamic Gaussian Splatting in Neural Motion Flow Field for Autonomous Driving
por: Sun, Su, et al.
Publicado: (2024)

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

FlowConsist: Make Your Flow Consistent with Real Trajectory
por: Zhang, Tianyi, et al.
Publicado: (2026)

SciFlow: Empowering Lightweight Optical Flow Models with Self-Cleaning Iterations
por: Lin, Jamie Menjay, et al.
Publicado: (2024)

AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows
por: Zhou, Zhenglin, et al.
Publicado: (2025)

VReST: Enhancing Reasoning in Large Vision-Language Models through Tree Search and Self-Reward Mechanism
por: Zhang, Congzhi, et al.
Publicado: (2025)

Goku: Flow Based Video Generative Foundation Models
por: Chen, Shoufa, et al.
Publicado: (2025)

TReFT: Taming Rectified Flow Models For One-Step Image Translation
por: Li, Shengqian, et al.
Publicado: (2025)

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model
por: AI, Inclusion, et al.
Publicado: (2026)

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
por: Zhu, Yuanzhi, et al.
Publicado: (2024)

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

MaskFlow: Discrete Flows For Flexible and Efficient Long Video Generation
por: Fuest, Michael, et al.
Publicado: (2025)

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

FACM: Flow-Anchored Consistency Models
por: Peng, Yansong, et al.
Publicado: (2025)

FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching Models
por: Sun, Yi, et al.
Publicado: (2026)

Self-Assessed Generation: Trustworthy Label Generation for Optical Flow and Stereo Matching in Real-world
por: Ling, Han, et al.
Publicado: (2024)

Self-Guidance: Boosting Flow and Diffusion Generation on Their Own
por: Li, Tiancheng, et al.
Publicado: (2024)

Few-step Flow for 3D Generation via Marginal-Data Transport Distillation
por: Zhou, Zanwei, et al.
Publicado: (2025)

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

Reversing the Flow: Generation-to-Understanding Synergy in Large Multimodal Models
por: Tong, Yujun, et al.
Publicado: (2026)

Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration
por: Sun, Xiaohui, et al.
Publicado: (2026)

FlowDreamer: Exploring High Fidelity Text-to-3D Generation via Rectified Flow
por: Li, Hangyu, et al.
Publicado: (2024)

U$^{2}$Flow: Uncertainty-Aware Unsupervised Optical Flow Estimation
por: Sun, Xunpei, 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)

Chain of Flow: A Foundational Generative Framework for ECG-to-4D Cardiac Digital Twins
por: Wu, Haofan, et al.
Publicado: (2026)

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

FlowComposer: Composable Flows for Compositional Zero-Shot Learning
por: He, Zhenqi, et al.
Publicado: (2026)

FastFlow: Accelerating The Generative Flow Matching Models with Bandit Inference
por: Bajpai, Divya Jyoti, et al.
Publicado: (2026)

A one-step generation model with a Single-Layer Transformer: Layer number re-distillation of FreeFlow
por: Wei, Haonan, et al.
Publicado: (2026)