Cover Image

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tong, Chengzhuo, Guo, Ziyu, Zhang, Renrui, Shan, Wenyu, Wei, Xinyu, Xing, Zhenghao, Li, Hongsheng, Heng, Pheng-Ann
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step
by: Guo, Ziyu, et al.
Published: (2025)

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
by: Jiang, Dongzhi, et al.
Published: (2025)

SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners
by: Guo, Ziyu, et al.
Published: (2024)

DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
by: Jiang, Dongzhi, et al.
Published: (2025)

Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark
by: Guo, Ziyu, et al.
Published: (2025)

Unveiling Deep Shadows: A Survey and Benchmark on Image and Video Shadow Detection, Removal, and Generation in the Deep Learning Era
by: Hu, Xiaowei, et al.
Published: (2024)

Thinking-while-Generating: Interleaving Textual Reasoning throughout Visual Generation
by: Guo, Ziyu, et al.
Published: (2025)

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency
by: Jiang, Dongzhi, et al.
Published: (2025)

ATLAS: Agentic or Latent Visual Reasoning? One Word is Enough for Both
by: Guo, Ziyu, et al.
Published: (2026)

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
by: Chen, Xinyan, et al.
Published: (2025)

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
by: Qiu, Longtian, et al.
Published: (2025)

It Takes Two: Your GRPO Is Secretly DPO
by: Wu, Yihong, et al.
Published: (2025)

MME-CoF-Pro: Evaluating Reasoning Coherence in Video Generative Models with Text and Visual Hints
by: Qi, Yu, et al.
Published: (2026)

MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding
by: Wang, Jiaze, et al.
Published: (2024)

Point Cloud Understanding via Attention-Driven Contrastive Learning
by: Wang, Yi, et al.
Published: (2024)

Does Engram Do Memory Retrieval in Autoregressive Image Generation?
by: Wang, Jinghao, et al.
Published: (2026)

MAVIS: Mathematical Visual Instruction Tuning with an Automatic Data Engine
by: Zhang, Renrui, et al.
Published: (2024)

Video Instance Shadow Detection Under the Sun and Sky
by: Xing, Zhenghao, et al.
Published: (2022)

Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs
by: Mohammadi, Hadi, et al.
Published: (2025)

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos
by: Lin, Weifeng, et al.
Published: (2025)

ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RL
by: Zhang, Yu, et al.
Published: (2025)

MS2Mesh-XR: Multi-modal Sketch-to-Mesh Generation in XR Environments
by: Tong, Yuqi, et al.
Published: (2024)

EchoInk-R1: Exploring Audio-Visual Reasoning in Multimodal LLMs via Reinforcement Learning
by: Xing, Zhenghao, et al.
Published: (2025)

Creating Virtual Environments with 3D Gaussian Splatting: A Comparative Study
by: Qiu, Shi, et al.
Published: (2025)

CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
by: Jiang, Dongzhi, et al.
Published: (2024)

SciVerse: Unveiling the Knowledge Comprehension and Visual Reasoning of LMMs on Multi-modal Scientific Problems
by: Guo, Ziyu, et al.
Published: (2025)

To CoT or not to CoT? Chain-of-thought helps mainly on math and symbolic reasoning
by: Sprague, Zayne, et al.
Published: (2024)

GIFT: Group-Relative Implicit Fine-Tuning Integrates GRPO with DPO and UNA
by: Wang, Zhichao
Published: (2025)

Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
by: Xu, Jiaqi, et al.
Published: (2026)

From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
by: Deng, Yuntian, et al.
Published: (2024)

PromptRL: Prompt Matters in RL for Flow-Based Image Generation
by: Wang, Fu-Yun, et al.
Published: (2026)

Uni-Synergy: Bridging Understanding and Generation for Personalized Reasoning via Co-operative Reinforcement Learning
by: Shen, Zijun, et al.
Published: (2026)

CodePlot-CoT: Mathematical Visual Reasoning by Thinking with Code-Driven Images
by: Duan, Chengqi, et al.
Published: (2025)

IMAGINE-E: Image Generation Intelligence Evaluation of State-of-the-art Text-to-Image Models
by: Lei, Jiayi, et al.
Published: (2025)

The Synergy Dilemma of Long-CoT SFT and RL: Investigating Post-Training Techniques for Reasoning VLMs
by: Chen, Jierun, et al.
Published: (2025)

Meta-CoT: Enhancing Granularity and Generalization in Image Editing
by: Zhang, Shiyi, et al.
Published: (2026)

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
by: Huang, Qihan, et al.
Published: (2024)

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
by: Ma, Xiaoxiao, et al.
Published: (2026)

DanceGRPO: Unleashing GRPO on Visual Generation
by: Xue, Zeyue, et al.
Published: (2025)

Advancing Extended Reality with 3D Gaussian Splatting: Innovations and Prospects
by: Qiu, Shi, et al.
Published: (2024)