Cover Image

Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Zhikai, Zhao, Yue, Zhang, Edward Zhongwei, Liu, Xuewen, Zhang, Jing, Gu, Qingyi, Dong, Zhen
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

K-Sort Arena: Efficient and Reliable Benchmarking for Generative Models via K-wise Human Preferences
by: Li, Zhikai, et al.
Published: (2024)

Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval
by: Zhang, Jing, et al.
Published: (2026)

CacheQuant: Comprehensively Accelerated Diffusion Models
by: Liu, Xuewen, et al.
Published: (2025)

SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model
by: Zhang, Jing, et al.
Published: (2025)

Rectified SpaAttn: Revisiting Attention Sparsity for Efficient Video Generation
by: Liu, Xuewen, et al.
Published: (2025)

PTQ4ARVG: Post-Training Quantization for AutoRegressive Visual Generation Models
by: Liu, Xuewen, et al.
Published: (2026)

Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare
by: Li, Zhikai, et al.
Published: (2024)

K-Sort Eval: Efficient Preference Evaluation for Visual Generation via Corrected VLM-as-a-Judge
by: Li, Zhikai, et al.
Published: (2026)

DilateQuant: Accurate and Efficient Diffusion Quantization via Weight Dilation
by: Liu, Xuewen, et al.
Published: (2024)

EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models
by: Liu, Xuewen, et al.
Published: (2024)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
by: Wu, Ziyi, et al.
Published: (2025)

VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
by: Xu, Jiazheng, et al.
Published: (2024)

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization
by: Zhang, Tao, et al.
Published: (2025)

MJ-VIDEO: Fine-Grained Benchmarking and Rewarding Video Preferences in Video Generation
by: Tong, Haibo, et al.
Published: (2025)

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction
by: Yang, Lianwei, et al.
Published: (2024)

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

Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
by: Fu, Minghao, et al.
Published: (2025)

DiffusionFF: A Diffusion-based Framework for Joint Face Forgery Detection and Fine-Grained Artifact Localization
by: Peng, Siran, et al.
Published: (2025)

Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs
by: Lu, Yunhong, et al.
Published: (2026)

BeautyGRPO: Aesthetic Alignment for Face Retouching via Dynamic Path Guidance and Fine-Grained Preference Modeling
by: Yang, Jiachen, et al.
Published: (2026)

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs
by: Shen, Yifan, et al.
Published: (2025)

Beyond Pairwise Preferences: Listwise Reward-Aware Alignment for Diffusion Models
by: Wang, Austin, et al.
Published: (2026)

Diffusion Models as Optimizers for Efficient Planning in Offline RL
by: Huang, Renming, et al.
Published: (2024)

RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution
by: Song, Yushuai, et al.
Published: (2026)

AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization
by: Li, Lanjiong, et al.
Published: (2025)

Improving Fine-Grained Control via Aggregation of Multiple Diffusion Models
by: Yue, Conghan, et al.
Published: (2024)

Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control
by: Han, Yue, et al.
Published: (2024)

Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization
by: Liang, Zhanhao, et al.
Published: (2024)

AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization
by: Liao, Jingyi, et al.
Published: (2025)

DRM: Diffusion-based Reward Model With Step-wise Guidance
by: Zhang, Jaxon, et al.
Published: (2026)

Reinforcing Diffusion Models by Direct Group Preference Optimization
by: Luo, Yihong, et al.
Published: (2025)

Token Preference Optimization with Self-Calibrated Visual-Anchored Rewards for Hallucination Mitigation
by: Gu, Jihao, et al.
Published: (2024)

Diffusion Distillation With Direct Preference Optimization For Efficient 3D LiDAR Scene Completion
by: Zhao, An, et al.
Published: (2025)

Fine-Grained Generalization via Structuralizing Concept and Feature Space into Commonality, Specificity and Confounding
by: Wang, Zhen, et al.
Published: (2026)

Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences
by: Lu, Yunhong, et al.
Published: (2025)

Discriminator-Free Direct Preference Optimization for Video Diffusion
by: Cheng, Haoran, et al.
Published: (2025)

Direct Preference Optimization of Video Large Multimodal Models from Language Model Reward
by: Zhang, Ruohong, et al.
Published: (2024)

Diffusion-NPO: Negative Preference Optimization for Better Preference Aligned Generation of Diffusion Models
by: Wang, Fu-Yun, et al.
Published: (2025)

InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment
by: Lu, Yunhong, et al.
Published: (2025)

Prompting Segment Anything Model with Domain-Adaptive Prototype for Generalizable Medical Image Segmentation
by: Wei, Zhikai, et al.
Published: (2024)