Cover Image

Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Jiadong, Li, Liang, Peng, Yuxin, Tang, Yu-Ming, Wang, Shuohuan, Sun, Yu, Wu, Hua, Huang, Qingming, Wang, Haifeng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Curiosity-Driven Reinforcement Learning from Human Feedback
by: Sun, Haoran, et al.
Published: (2025)

CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models
by: Hao, Xiangzhao, et al.
Published: (2026)

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

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction
by: Ji, Longbin, et al.
Published: (2026)

Tool-Augmented Reward Modeling
by: Li, Lei, et al.
Published: (2023)

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions
by: Chai, Yekun, et al.
Published: (2024)

V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention
by: Sun, Nan, et al.
Published: (2025)

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
by: Wu, Chengyue, et al.
Published: (2024)

Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
by: Chen, Xiaokang, et al.
Published: (2025)

On Training Data Influence of GPT Models
by: Chai, Yekun, et al.
Published: (2024)

Upcycling Instruction Tuning from Dense to Mixture-of-Experts via Parameter Merging
by: Hui, Tingfeng, et al.
Published: (2024)

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

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
by: Hong, Jixiang, et al.
Published: (2025)

UniModel: A Visual-Only Framework for Unified Multimodal Understanding and Generation
by: Zhang, Chi, et al.
Published: (2025)

JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation
by: Ma, Yiyang, et al.
Published: (2024)

VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model
by: Zhuang, Xianwei, et al.
Published: (2025)

MMGen: Unified Multi-modal Image Generation and Understanding in One Go
by: Wang, Jiepeng, et al.
Published: (2025)

Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
by: Wang, Xiaokun, et al.
Published: (2025)

USO: Unified Style and Subject-Driven Generation via Disentangled and Reward Learning
by: Wu, Shaojin, et al.
Published: (2025)

UniEval: Unified Holistic Evaluation for Unified Multimodal Understanding and Generation
by: Li, Yi, et al.
Published: (2025)

BeamLoRA: Beam-Constraint Low-Rank Adaptation
by: Gu, Naibin, et al.
Published: (2025)

Advantageous Parameter Expansion Training Makes Better Large Language Models
by: Gu, Naibin, et al.
Published: (2025)

Unsafe by Reciprocity: How Generation-Understanding Coupling Undermines Safety in Unified Multimodal Models
by: Wang, Kaishen, et al.
Published: (2026)

UniMesh: Unifying 3D Mesh Understanding and Generation
by: Huang, Peng, et al.
Published: (2026)

MME-Unify: A Comprehensive Benchmark for Unified Multimodal Understanding and Generation Models
by: Xie, Wulin, et al.
Published: (2025)

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
by: Liao, Kang, et al.
Published: (2025)

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
by: Jiang, Jingjing, et al.
Published: (2025)

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
by: Zhao, Shanshan, et al.
Published: (2025)

Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
by: Tang, Wei, et al.
Published: (2024)

VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video Understanding
by: Zhang, Zhihong, et al.
Published: (2025)

Harmonizing Visual Representations for Unified Multimodal Understanding and Generation
by: Wu, Size, et al.
Published: (2025)

NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
by: Zhang, Huichao, et al.
Published: (2026)

Mixture of Hidden-Dimensions Transformer
by: Chen, Yilong, et al.
Published: (2024)

Exploring Hallucination of Large Multimodal Models in Video Understanding: Benchmark, Analysis and Mitigation
by: Gao, Hongcheng, et al.
Published: (2025)

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation
by: Qu, Liao, et al.
Published: (2024)

SafeCFG: Controlling Harmful Features with Dynamic Safe Guidance for Safe Generation
by: Pan, Jiadong, et al.
Published: (2024)

Autoregressive Pre-Training on Pixels and Texts
by: Chai, Yekun, et al.
Published: (2024)

HFT: Half Fine-Tuning for Large Language Models
by: Hui, Tingfeng, et al.
Published: (2024)

UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing
by: Tang, Hao, et al.
Published: (2025)

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