Cover Image

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Shaojin, Huang, Mengqi, Cheng, Yufeng, Wu, Wenxu, Tian, Jiahe, Luo, Yiming, Ding, Fei, He, Qian
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
by: Cheng, Yufeng, et al.
Published: (2025)

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
by: Wu, Shaojin, et al.
Published: (2025)

VMix: Improving Text-to-Image Diffusion Model with Cross-Attention Mixing Control
by: Wu, Shaojin, et al.
Published: (2024)

DreamO: A Unified Framework for Image Customization
by: Mou, Chong, et al.
Published: (2025)

Stream-R1: Reliability-Perplexity Aware Reward Distillation for Streaming Video Generation
by: Wu, Bin, et al.
Published: (2026)

Lance: Unified Multimodal Modeling by Multi-Task Synergy
by: Fu, Fengyi, et al.
Published: (2026)

UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement
by: Yang, Jingwei, et al.
Published: (2026)

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
by: Pan, Jiadong, et al.
Published: (2026)

Stream-T1: Test-Time Scaling for Streaming Video Generation
by: Tu, Yijing, et al.
Published: (2026)

Disentangled Latent Energy-Based Style Translation: An Image-Level Structural MRI Harmonization Framework
by: Wu, Mengqi, et al.
Published: (2024)

RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
by: Lin, Yijing, et al.
Published: (2025)

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
by: Chen, Hong, et al.
Published: (2023)

3SGen: Unified Subject, Style, and Structure-Driven Image Generation with Adaptive Task-specific Memory
by: Song, Xinyang, et al.
Published: (2025)

Unsupervised Disentanglement of Content and Style via Variance-Invariance Constraints
by: Wu, Yuxuan, et al.
Published: (2024)

Unified Multi-Site Multi-Sequence Brain MRI Harmonization Enriched by Biomedical Semantic Style
by: Wu, Mengqi, et al.
Published: (2026)

PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
by: Wang, Shulei, et al.
Published: (2025)

OneReward: Unified Mask-Guided Image Generation via Multi-Task Human Preference Learning
by: Gong, Yuan, et al.
Published: (2025)

LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
by: Fu, Fengyi, et al.
Published: (2025)

CDST: Color Disentangled Style Transfer for Universal Style Reference Customization
by: Zhang, Shiwen, et al.
Published: (2025)

PRPO: Aligning Process Reward with Outcome Reward in Policy Optimization
by: Ding, Ruiyi, et al.
Published: (2026)

MultiCrafter: High-Fidelity Multi-Subject Generation via Disentangled Attention and Identity-Aware Preference Alignment
by: Wu, Tao, et al.
Published: (2025)

DDNet: A Dual-Stream Graph Learning and Disentanglement Framework for Temporal Forgery Localization
by: Zhao, Boyang, et al.
Published: (2026)

ConDSeg: A General Medical Image Segmentation Framework via Contrast-Driven Feature Enhancement
by: Lei, Mengqi, et al.
Published: (2024)

VE-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment
by: Sun, Shangkun, et al.
Published: (2024)

MUSE: Multi-Subject Unified Synthesis via Explicit Layout Semantic Expansion
by: Peng, Fei, et al.
Published: (2025)

Learning What Matters: Dynamic Dimension Selection and Aggregation for Interpretable Vision-Language Reward Modeling
by: Chen, Qiyuan, et al.
Published: (2026)

VideoPDE: Unified Generative PDE Solving via Video Inpainting Diffusion Models
by: Li, Edward, et al.
Published: (2025)

RealCustom++: Representing Images as Real Textual Word for Real-Time Customization
by: Mao, Zhendong, et al.
Published: (2024)

Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights
by: Tian, Juanxi, et al.
Published: (2025)

MUSAR: Exploring Multi-Subject Customization from Single-Subject Dataset via Attention Routing
by: Guo, Zinan, et al.
Published: (2025)

PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
by: Chen, Sixiang, et al.
Published: (2026)

Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
by: Wang, Yuran, et al.
Published: (2025)

CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization
by: Chen, Nan, et al.
Published: (2024)

StyleDecoupler: Generalizable Artistic Style Disentanglement
by: Jia, Zexi, et al.
Published: (2026)

CIV-DG: Conditional Instrumental Variables for Domain Generalization in Medical Imaging
by: Bai, Shaojin, et al.
Published: (2026)

I2VControl: Disentangled and Unified Video Motion Synthesis Control
by: Feng, Wanquan, et al.
Published: (2024)

Disentangling to Re-couple: Resolving the Similarity-Controllability Paradox in Subject-Driven Text-to-Image Generation
by: Li, Shuang, et al.
Published: (2026)

Unified Reward Model for Multimodal Understanding and Generation
by: Wang, Yibin, et al.
Published: (2025)

WikiStyle+: A Multimodal Approach to Content-Style Representation Disentanglement for Artistic Image Stylization
by: Zhuoqi, Ma, et al.
Published: (2024)

DreamStyle: A Unified Framework for Video Stylization
by: Li, Mengtian, et al.
Published: (2026)