Imagen de Portada

PromptEcho: Annotation-Free Reward from Vision-Language Models for Text-to-Image Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Liu, Jinlong, He, Wanggui, Zhang, Peng, Liu, Mushui, Jiang, Hao, Huang, Pipei
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

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

DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
por: Zhang, Peng, et al.
Publicado: (2026)

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

Boosting MLLM Reasoning with Text-Debiased Hint-GRPO
por: Huang, Qihan, et al.
Publicado: (2025)

MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis
por: He, Wanggui, et al.
Publicado: (2024)

DCoAR: Deep Concept Injection into Unified Autoregressive Models for Personalized Text-to-Image Generation
por: Wu, Fangtai, et al.
Publicado: (2025)

Towards Enhanced Image Generation Via Multi-modal Chain of Thought in Unified Generative Models
por: Wang, Yi, et al.
Publicado: (2025)

Self-Rewarding Large Vision-Language Models for Optimizing Prompts in Text-to-Image Generation
por: Yang, Hongji, et al.
Publicado: (2025)

CMMCoT: Enhancing Complex Multi-Image Comprehension via Multi-Modal Chain-of-Thought and Memory Augmentation
por: Zhang, Guanghao, et al.
Publicado: (2025)

MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance
por: Wang, Xierui, et al.
Publicado: (2024)

Unified Prompt Attack Against Text-to-Image Generation Models
por: Peng, Duo, et al.
Publicado: (2025)

Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
por: Cui, Bowen, et al.
Publicado: (2026)

Debiased Prompt Tuning in Vision-Language Model without Annotations
por: Jiang, Chaoquan, et al.
Publicado: (2025)

Hierarchical Cross-modal Prompt Learning for Vision-Language Models
por: Zheng, Hao, et al.
Publicado: (2025)

Tuning-Free Image Customization with Image and Text Guidance
por: Li, Pengzhi, et al.
Publicado: (2024)

VLM-CPL: Consensus Pseudo Labels from Vision-Language Models for Annotation-Free Pathological Image Classification
por: Zhong, Lanfeng, et al.
Publicado: (2024)

Hybrid Mask Generation for Infrared Small Target Detection with Single-Point Supervision
por: He, Weijie, et al.
Publicado: (2024)

Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
por: Huang, Qihan, et al.
Publicado: (2024)

DyST-XL: Dynamic Layout Planning and Content Control for Compositional Text-to-Video Generation
por: He, Weijie, et al.
Publicado: (2025)

Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
por: Wang, Yifan, et al.
Publicado: (2025)

Understanding Reward Hacking in Text-to-Image Reinforcement Learning
por: Hong, Yunqi, et al.
Publicado: (2026)

OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning
por: Liu, Mushui, et al.
Publicado: (2024)

Fully Fine-tuned CLIP Models are Efficient Few-Shot Learners
por: Liu, Mushui, et al.
Publicado: (2024)

Learning to Prompt with Text Only Supervision for Vision-Language Models
por: Khattak, Muhammad Uzair, et al.
Publicado: (2024)

Bridging Visual Representation and Reinforcement Learning from Verifiable Rewards in Large Vision-Language Models
por: Han, Yuhang, et al.
Publicado: (2026)

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
por: Mao, Weijia, et al.
Publicado: (2025)

T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
por: Huang, Ziwei, et al.
Publicado: (2024)

Annotation-Free Curb Detection Leveraging Altitude Difference Image
por: Ma, Fulong, et al.
Publicado: (2024)

Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning
por: Liu, Mushui, et al.
Publicado: (2024)

Deep Reward Supervisions for Tuning Text-to-Image Diffusion Models
por: Wu, Xiaoshi, et al.
Publicado: (2024)

EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
por: Zhang, Yuxuan, et al.
Publicado: (2024)

Prompt-Softbox-Prompt: A Free-Text Embedding Control for Image Editing
por: Yang, Yitong, et al.
Publicado: (2024)

Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation
por: Bai, Weimin, et al.
Publicado: (2025)

Reinforcement Learning with Inverse Rewards for World Model Post-training
por: Ye, Yang, et al.
Publicado: (2025)

TextRefiner: Internal Visual Feature as Efficient Refiner for Vision-Language Models Prompt Tuning
por: Xie, Jingjing, et al.
Publicado: (2024)

Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
por: Zhu, Jingyuan, et al.
Publicado: (2026)

CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image Captioning
por: Tang, Zhijiang, et al.
Publicado: (2026)

Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
por: Xiao, Wenyi, et al.
Publicado: (2024)

HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
por: Shi, Senyuan, et al.
Publicado: (2026)

Integrated Structural Prompt Learning for Vision-Language Models
por: Wang, Jiahui, et al.
Publicado: (2025)