Cover Image

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Runhui, Wu, Jie, Yang, Rui, Liu, Zhe, Zhao, Hengshuang
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DrivePI: Spatial-aware 4D MLLM for Unified Autonomous Driving Understanding, Perception, Prediction and Planning
by: Liu, Zhe, et al.
Published: (2025)

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

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

HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding
by: Yang, Rui, et al.
Published: (2025)

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

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

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs
by: Gao, Xin, et al.
Published: (2026)

Self-Rewarding Vision-Language Model via Reasoning Decomposition
by: Li, Zongxia, et al.
Published: (2025)

Rethinking Reward Signals in Video GRPO: When Scores Become Targets
by: Li, Rui, et al.
Published: (2025)

Alchemist: Unlocking Efficiency in Text-to-Image Model Training via Meta-Gradient Data Selection
by: Ding, Kaixin, et al.
Published: (2025)

Syn-GRPO: Self-Evolving Data Synthesis for MLLM Perception Reasoning
by: Huang, Qihan, et al.
Published: (2025)

Can Atomic Step Decomposition Enhance the Self-structured Reasoning of Multimodal Large Models?
by: Xiang, Kun, et al.
Published: (2025)

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

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

DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO
by: Liu, Henglin, et al.
Published: (2025)

Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO
by: Tong, Yunze, et al.
Published: (2026)

OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces
by: Wang, Zehan, et al.
Published: (2024)

Enhancing Spatial Understanding in Image Generation via Reward Modeling
by: Tang, Zhenyu, et al.
Published: (2026)

UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation
by: Yang, Lihe, et al.
Published: (2024)

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

AeSlides: Incentivizing Aesthetic Layout in LLM-Based Slide Generation via Verifiable Rewards
by: Pan, Yiming, et al.
Published: (2026)

TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
by: He, Xiaoxuan, et al.
Published: (2025)

Active-O3: Empowering Multimodal Large Language Models with Active Perception via GRPO
by: Zhu, Muzhi, et al.
Published: (2025)

Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning
by: Cheng, Hanbo, et al.
Published: (2026)

RewardDance: Reward Scaling in Visual Generation
by: Wu, Jie, et al.
Published: (2025)

Video Models Can Reason with Verifiable Rewards
by: Zhu, Tinghui, et al.
Published: (2026)

HiRes-LLaVA: Restoring Fragmentation Input in High-Resolution Large Vision-Language Models
by: Huang, Runhui, et al.
Published: (2024)

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

ILLUME+: Illuminating Unified MLLM with Dual Visual Tokenization and Diffusion Refinement
by: Huang, Runhui, et al.
Published: (2025)

Taming Camera-Controlled Video Generation with Verifiable Geometry Reward
by: Wang, Zhaoqing, et al.
Published: (2025)

FocalClick-XL: Towards Unified and High-quality Interactive Segmentation
by: Chen, Xi, et al.
Published: (2025)

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

DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
by: Zuo, Yi, et al.
Published: (2026)

Federated Out-of-Distribution Generalization: A Causal Augmentation View
by: Zhang, Runhui, et al.
Published: (2025)

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning
by: Ji, Sihui, 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)

MIRROR: Multimodal Iterative Reasoning via Reflection on Visual Regions
by: Zhang, Haoyu, et al.
Published: (2026)

Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
by: Ling, Pengyang, et al.
Published: (2026)

GDRO: Group-level Reward Post-training Suitable for Diffusion Models
by: Wang, Yiyang, et al.
Published: (2026)

Action Draft and Verify: A Self-Verifying Framework for Vision-Language-Action Model
by: Zhao, Chen, et al.
Published: (2026)