Cover Image

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jiaqi, Deng, Haoge, Pan, Ting, Liu, Yang, Wang, Chengyuan, Zhang, Fan, Qi, Yonggang, Wang, Xinlong
Format:	Preprint
Published:	2026
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

Uniform Discrete Diffusion with Metric Path for Video Generation
by: Deng, Haoge, et al.
Published: (2025)

Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Diffusion Model
by: Zhou, Renping, et al.
Published: (2025)

Autoregressive Video Generation without Vector Quantization
by: Deng, Haoge, et al.
Published: (2024)

LINA: Linear Autoregressive Image Generative Models with Continuous Tokens
by: Wang, Jiahao, et al.
Published: (2026)

BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models
by: Li, Yuming, et al.
Published: (2025)

Flash-GRPO: Efficient Alignment for Video Diffusion via One-Step Policy Optimization
by: He, Xiaoxuan, et al.
Published: (2026)

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
by: Wang, Yibin, et al.
Published: (2025)

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
by: Diao, Haiwen, et al.
Published: (2025)

You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale
by: Ma, Baorui, et al.
Published: (2024)

OP-GRPO: Efficient Off-Policy GRPO for Flow-Matching Models
by: Zhang, Liyu, et al.
Published: (2026)

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery
by: Yao, Nanjie, et al.
Published: (2026)

FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
by: Wang, Qiang, et al.
Published: (2025)

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
by: Liu, Jie, et al.
Published: (2026)

CI-VID: A Coherent Interleaved Text-Video Dataset
by: Ju, Yiming, et al.
Published: (2025)

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

Emu3.5: Native Multimodal Models are World Learners
by: Cui, Yufeng, et al.
Published: (2025)

Tokenize Anything via Prompting
by: Pan, Ting, et al.
Published: (2023)

Region-Constrained Group Relative Policy Optimization for Flow-Based Image Editing
by: Ouyang, Zhuohan, et al.
Published: (2026)

Towards Unified Multimodal Interleaved Generation via Group Relative Policy Optimization
by: Nie, Ming, et al.
Published: (2026)

Group Relative Policy Optimization for Image Captioning
by: Liang, Xu
Published: (2025)

Diffusion Feedback Helps CLIP See Better
by: Wang, Wenxuan, et al.
Published: (2024)

Multi-Reward GRPO for Stable and Prosodic Single-Codebook TTS LLMs at Scale
by: Zhong, Yicheng, et al.
Published: (2025)

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
by: Rong, Xuankun, et al.
Published: (2025)

On Discrete Prompt Optimization for Diffusion Models
by: Wang, Ruochen, et al.
Published: (2024)

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space
by: Bu, Jiazi, et al.
Published: (2026)

STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation
by: Ma, Xiaoxiao, et al.
Published: (2025)

Fine-Grained GRPO for Precise Preference Alignment in Flow Models
by: Zhou, Yujie, et al.
Published: (2025)

VideoMiner: Iteratively Grounding Key Frames of Hour-Long Videos via Tree-based Group Relative Policy Optimization
by: Cao, Xinye, et al.
Published: (2025)

A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization
by: Zhu, Jinchao, et al.
Published: (2023)

Relational Diffusion Distillation for Efficient Image Generation
by: Feng, Weilun, et al.
Published: (2024)

SparseDiT: Token Sparsification for Efficient Diffusion Transformer
by: Chang, Shuning, et al.
Published: (2024)

Computer-Aided Design Generation by Cascaded Discrete Diffusion Model
by: Pan, Honghu, et al.
Published: (2026)

AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning
by: Yuan, Shihao, et al.
Published: (2025)

FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
by: Dai, Yixiang, et al.
Published: (2025)

Multi-GRPO: Multi-Group Advantage Estimation for Text-to-Image Generation with Tree-Based Trajectories and Multiple Rewards
by: Lyu, Qiang, et al.
Published: (2025)

FIND: Fine-tuning Initial Noise Distribution with Policy Optimization for Diffusion Models
by: Chen, Changgu, et al.
Published: (2024)

GPO-V: Jailbreak Diffusion Vision Language Model by Global Probability Optimization
by: Pan, Yu, et al.
Published: (2026)

MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
by: Li, Junzhe, et al.
Published: (2025)

GRIP-VLM: Group-Relative Importance Pruning for Efficient Vision-Language Models
by: Huang, Mingzhe, et al.
Published: (2026)

DenseGRPO: From Sparse to Dense Reward for Flow Matching Model Alignment
by: Deng, Haoyou, et al.
Published: (2026)