Imagen de Portada

DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yang, Hanqing, Zhou, Qiang, Du, Yongchao, Zhou, Sashuai, Wang, Zhibin, Song, Jun, Ge, Tiezheng, Yu, Cheng, Zheng, Bo
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unified Thinker: A General Reasoning Modular Core for Image Generation
por: Zhou, Sashuai, et al.
Publicado: (2026)

Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement Learning
por: Ma, Yinchao, 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)

Edit-GRPO: A Locality-Preserving Policy Optimization Framework for Image Editing
por: Xu, Shaodong, et al.
Publicado: (2026)

Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking
por: Xu, Mingyi, et al.
Publicado: (2026)

RHanDS: Refining Malformed Hands for Generated Images with Decoupled Structure and Style Guidance
por: Wang, Chengrui, et al.
Publicado: (2024)

DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic Surgery
por: Zhou, Yuning, et al.
Publicado: (2024)

LiDDA: Data Driven Attribution at LinkedIn
por: Bencina, John, et al.
Publicado: (2025)

CellSeg1: Robust Cell Segmentation with One Training Image
por: Zhou, Peilin, et al.
Publicado: (2024)

Video-Thinker: Sparking "Thinking with Videos" via Reinforcement Learning
por: Wang, Shijian, et al.
Publicado: (2025)

PreferThinker: Reasoning-based Personalized Image Preference Assessment
por: Xu, Shengqi, et al.
Publicado: (2025)

Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
por: Xu, Sen, et al.
Publicado: (2025)

GAN-based Domain Adaptation for Image-aware Layout Generation in Advertising Poster Design
por: Xu, Chenchen, et al.
Publicado: (2026)

ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
por: Zhang, Congzhi, et al.
Publicado: (2025)

Decoupling Reasoning and Knowledge Injection for In-Context Knowledge Editing
por: Wang, Changyue, et al.
Publicado: (2025)

SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
por: Zhang, Ruiyang, et al.
Publicado: (2026)

EditThinker: Unlocking Iterative Reasoning for Any Image Editor
por: Li, Hongyu, et al.
Publicado: (2025)

VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning
por: Wang, Chaoyang, et al.
Publicado: (2026)

TBStar-Edit: From Image Editing Pattern Shifting to Consistency Enhancement
por: Fang, Hao, et al.
Publicado: (2025)

Enhancing Multi-modal Models with Heterogeneous MoE Adapters for Fine-tuning
por: Zhou, Sashuai, et al.
Publicado: (2025)

GraphThinker: Reinforcing Temporally Grounded Video Reasoning with Event Graph Thinking
por: Cheng, Zixu, et al.
Publicado: (2026)

From Competition to Synergy: Unlocking Reinforcement Learning for Subject-Driven Image Generation
por: Huang, Ziwei, et al.
Publicado: (2025)

Accelerating Image Generation with Sub-path Linear Approximation Model
por: Xu, Chen, et al.
Publicado: (2024)

KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation
por: Zhang, Dalong, et al.
Publicado: (2025)

OneThinker: All-in-one Reasoning Model for Image and Video
por: Feng, Kaituo, et al.
Publicado: (2025)

OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling
por: Wang, Zengzhi, et al.
Publicado: (2025)

FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution
por: Wang, Shuai, et al.
Publicado: (2024)

I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
por: Ma, Yiwei, et al.
Publicado: (2024)

DMM: Building a Versatile Image Generation Model via Distillation-Based Model Merging
por: Song, Tianhui, et al.
Publicado: (2025)

T-Stars-Poster: A Framework for Product-Centric Advertising Image Design
por: Chen, Hongyu, et al.
Publicado: (2025)

MoreStyle: Relax Low-frequency Constraint of Fourier-based Image Reconstruction in Generalizable Medical Image Segmentation
por: Zhao, Haoyu, et al.
Publicado: (2024)

DGAI: Decoupled On-Disk Graph-Based ANN Index for Efficient Updates and Queries
por: Lou, Jiahao, et al.
Publicado: (2025)

Pest-Thinker: Learning to Think and Reason like Entomologists via Reinforcement Learning
por: Li, Xueheng, et al.
Publicado: (2026)

GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding
por: Ma, Junpeng, et al.
Publicado: (2026)

FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing
por: Jiang, Yilei, et al.
Publicado: (2025)

DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
por: He, Zefeng, et al.
Publicado: (2025)

VC4VG: Optimizing Video Captions for Text-to-Video Generation
por: Du, Yang, et al.
Publicado: (2025)

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
por: Wang, Qunzhong, et al.
Publicado: (2025)

WIA-LD2ND: Wavelet-based Image Alignment for Self-supervised Low-Dose CT Denoising
por: Zhao, Haoyu, et al.
Publicado: (2024)

Progressive Retinal Image Registration via Global and Local Deformable Transformations
por: Liu, Yepeng, et al.
Publicado: (2024)