Imagen de Portada

Online Reward-Weighted Fine-Tuning of Flow Matching with Wasserstein Regularization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Fan, Jiajun, Shen, Shuaike, Cheng, Chaoran, Chen, Yuxin, Liang, Chumeng, Liu, Ge
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence 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

Fine-tuning Flow Matching Generative Models with Intermediate Feedback
por: Fan, Jiajun, et al.
Publicado: (2025)

Flow-GRPO: Training Flow Matching Models via Online RL
por: Liu, Jie, et al.
Publicado: (2025)

Score-Regularized Joint Sampling with Importance Weights for Flow Matching
por: Liu, Xinshuang, et al.
Publicado: (2025)

Targeted Attack Improves Protection against Unauthorized Diffusion Customization
por: Zheng, Boyang, et al.
Publicado: (2023)

Reward Score Matching: Unifying Reward-based Fine-tuning for Flow and Diffusion Models
por: Lee, Jeongjae, et al.
Publicado: (2026)

Toward effective protection against diffusion based mimicry through score distillation
por: Xue, Haotian, et al.
Publicado: (2023)

M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual Reasoning
por: Yang, Bangji, et al.
Publicado: (2026)

R$^{2}$Seg: Training-Free OOD Medical Tumor Segmentation via Anatomical Reasoning and Statistical Rejection
por: Shen, Shuaike, et al.
Publicado: (2025)

Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization
por: Liu, Ke, et al.
Publicado: (2025)

Gradient-based Fine-Tuning through Pre-trained Model Regularization
por: Liu, Xuanbo, et al.
Publicado: (2025)

Geometric Point Attention Transformer for 3D Shape Reassembly
por: Li, Jiahan, et al.
Publicado: (2024)

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
por: Fan, Jiajun, et al.
Publicado: (2025)

WRF4CIR: Weight-Regularized Fine-Tuning Network for Composed Image Retrieval
por: Xu, Yizhuo, et al.
Publicado: (2026)

Visual Agentic Reinforcement Fine-Tuning
por: Liu, Ziyu, et al.
Publicado: (2025)

DEMO: Disentangled Motion Latent Flow Matching for Fine-Grained Controllable Talking Portrait Synthesis
por: Chen, Peiyin, et al.
Publicado: (2025)

TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization
por: Jing, Xuepeng, et al.
Publicado: (2026)

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
por: Yang, Kai, et al.
Publicado: (2023)

Fine-Tuning is Fine, if Calibrated
por: Mai, Zheda, et al.
Publicado: (2024)

ReflexFlow: Rethinking Learning Objective for Exposure Bias Alleviation in Flow Matching
por: Huang, Guanbo, et al.
Publicado: (2025)

Flow-OPD: On-Policy Distillation for Flow Matching Models
por: Fang, Zhen, et al.
Publicado: (2026)

HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation
por: Wen, Yuxin, et al.
Publicado: (2025)

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
por: Zeng, Xinyu, et al.
Publicado: (2026)

SpatialReward: Verifiable Spatial Reward Modeling for Fine-Grained Spatial Consistency in Text-to-Image Generation
por: Zhou, Sashuai, et al.
Publicado: (2026)

The Velocity Deficit: Initial Energy Injection for Flow Matching
por: Li, Linze, et al.
Publicado: (2026)

TrajFlow: Multi-modal Motion Prediction via Flow Matching
por: Yan, Qi, et al.
Publicado: (2025)

InjectFlow: Weak Guides Strong via Orthogonal Injection for Flow Matching
por: Wang, Dayu, et al.
Publicado: (2026)

Hierarchy-Aware Fine-Tuning of Vision-Language Models
por: Li, Jiayu, et al.
Publicado: (2025)

Segment Any Anomaly without Training via Hybrid Prompt Regularization
por: Cao, Yunkang, et al.
Publicado: (2023)

RewardFlow: Generate Images by Optimizing What You Reward
por: Susladkar, Onkar, et al.
Publicado: (2026)

SGMatch: Semantic-Guided Non-Rigid Shape Matching with Flow Regularization
por: Ye, Tianwei, et al.
Publicado: (2026)

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
por: Xu, Yifang, et al.
Publicado: (2025)

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
por: Wu, Xiaoshi, et al.
Publicado: (2024)

Remodeling Semantic Relationships in Vision-Language Fine-Tuning
por: Wu, Xiangyang, et al.
Publicado: (2025)

Semantic Generative Tuning for Unified Multimodal Models
por: Yu, Songsong, et al.
Publicado: (2026)

VeCoR -- Velocity Contrastive Regularization for Flow Matching
por: Hong, Zong-Wei, et al.
Publicado: (2025)

Online,Target-Free LiDAR-Camera Extrinsic Calibration via Cross-Modal Mask Matching
por: Huang, Zhiwei, et al.
Publicado: (2024)

REMAP: Regularized Matching and Partial Alignment of Video Embeddings
por: Chandra, Soumyadeep, et al.
Publicado: (2025)

Towards Calibrated Robust Fine-Tuning of Vision-Language Models
por: Oh, Changdae, et al.
Publicado: (2023)

HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning
por: Kim, Donggyun, et al.
Publicado: (2025)

Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning
por: Ning, Xin, et al.
Publicado: (2026)