Image de couverture de livre

Know Your Step: Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yue, Zhixiong, Ni, Zixuan, Ye, Feiyang, Zhang, Jinshan, Shen, Sheng, Mi, Zhenpeng
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

RenderFlow: Single-Step Neural Rendering via Flow Matching
par: Zhang, Shenghao, et autres
Publié: (2026)

LeapAlign: Post-Training Flow Matching Models at Any Generation Step by Building Two-Step Trajectories
par: Liang, Zhanhao, et autres
Publié: (2026)

FlowIID: Single-Step Intrinsic Image Decomposition via Latent Flow Matching
par: Singla, Mithlesh, et autres
Publié: (2026)

Denoising Diffusion Step-aware Models
par: Yang, Shuai, et autres
Publié: (2023)

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

FREE: Faster and Better Data-Free Meta-Learning
par: Wei, Yongxian, et autres
Publié: (2024)

StepAL: Step-aware Active Learning for Cataract Surgical Videos
par: Shah, Nisarg A., et autres
Publié: (2025)

Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
par: Chen, Hao, et autres
Publié: (2025)

Step by Step Network
par: Han, Dongchen, et autres
Publié: (2025)

Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
par: Ma, Xiaoxiao, et autres
Publié: (2025)

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

BiFM: Bidirectional Flow Matching for Few-Step Image Editing and Generation
par: Dai, Yasong, et autres
Publié: (2026)

Let's Reward Step-by-Step: Step-Aware Contrastive Alignment for Vision-Language Navigation in Continuous Environments
par: Li, Haoyuan, et autres
Publié: (2026)

Setting-Matched and Semantics-Scaled Benchmarking of One-Step Generative Models Against Multistep Diffusion and Flow Models
par: Ravishankar, Advaith, et autres
Publié: (2026)

Learning Few-Step Diffusion Models by Trajectory Distribution Matching
par: Luo, Yihong, et autres
Publié: (2025)

StepNet: Spatial-temporal Part-aware Network for Isolated Sign Language Recognition
par: Shen, Xiaolong, et autres
Publié: (2022)

OPCap:Object-aware Prompting Captioning
par: Huang, Feiyang
Publié: (2024)

DirectEdit: Step-Level Accurate Inversion for Flow-Based Image Editing
par: Yang, Desong, et autres
Publié: (2026)

Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
par: Sabour, Amirmojtaba, et autres
Publié: (2024)

RoMa v2: Harder Better Faster Denser Feature Matching
par: Edstedt, Johan, et autres
Publié: (2025)

Knowing Your Target: Target-Aware Transformer Makes Better Spatio-Temporal Video Grounding
par: Gu, Xin, et autres
Publié: (2025)

ViTOC: Vision Transformer and Object-aware Captioner
par: Huang, Feiyang
Publié: (2024)

Watch Your Step: Optimal Retrieval for Continual Learning at Scale
par: Hickok, Truman, et autres
Publié: (2024)

InstaRevive: One-Step Image Enhancement via Dynamic Score Matching
par: Zhu, Yixuan, et autres
Publié: (2025)

Text-to-Image Alignment in Denoising-Based Models through Step Selection
par: Grimal, Paul, et autres
Publié: (2025)

Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt
par: Zhang, Zhanjie, et autres
Publié: (2024)

CAFlow: Adaptive-Depth Single-Step Flow Matching for Efficient Histopathology Super-Resolution
par: Yoshai, Elad, et autres
Publié: (2026)

SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow
par: Zhu, Yuanzhi, et autres
Publié: (2024)

SoFlow: Solution Flow Models for One-Step Generative Modeling
par: Luo, Tianze, et autres
Publié: (2025)

Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
par: Liu, Tao, 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)

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation
par: Shen, Tingrui, et autres
Publié: (2025)

EchoLVFM: One-Step Video Generation via Latent Flow Matching for Echocardiogram Synthesis
par: Oladokun, Emmanuel, et autres
Publié: (2026)

SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation
par: Hu, Zixuan, et autres
Publié: (2025)

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft
par: Zhao, Zhonghan, et autres
Publié: (2024)

Watch Your Steps: Local Image and Scene Editing by Text Instructions
par: Mirzaei, Ashkan, et autres
Publié: (2023)

Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment
par: Schusterbauer, Johannes, et autres
Publié: (2025)

Consistency Trajectory Matching for One-Step Generative Super-Resolution
par: You, Weiyi, et autres
Publié: (2025)

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
par: He, Xiaoxuan, et autres
Publié: (2026)

ReAlign: Text-to-Motion Generation via Step-Aware Reward-Guided Alignment
par: Weng, Wanjiang, et autres
Publié: (2025)