Buchumschlag

Rule-Based Reinforcement Learning for Document Image Classification with Vision Language Models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Jungo, Michael, Fischer, Andreas
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Zero-Shot Prompting and Few-Shot Fine-Tuning: Revisiting Document Image Classification Using Large Language Models
von: Scius-Bertrand, Anna, et al.
Veröffentlicht: (2024)

DocThinker: Explainable Multimodal Large Language Models with Rule-based Reinforcement Learning for Document Understanding
von: Yu, Wenwen, et al.
Veröffentlicht: (2025)

Large Language Models Facilitate Vision Reflection in Image Classification
von: An, Guoyuan, et al.
Veröffentlicht: (2025)

Unified Reinforcement and Imitation Learning for Vision-Language Models
von: Lee, Byung-Kwan, et al.
Veröffentlicht: (2025)

Data Adaptive Traceback for Vision-Language Foundation Models in Image Classification
von: Peng, Wenshuo, et al.
Veröffentlicht: (2024)

Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification
von: Addepalli, Sravanti, et al.
Veröffentlicht: (2023)

Queryable Prototype Multiple Instance Learning with Vision-Language Models for Incremental Whole Slide Image Classification
von: Gou, Jiaxiang, et al.
Veröffentlicht: (2024)

DIVA-DAF: A Deep Learning Framework for Historical Document Image Analysis
von: Vögtlin, Lars, et al.
Veröffentlicht: (2022)

DocXplain: A Novel Model-Agnostic Explainability Method for Document Image Classification
von: Saifullah, Saifullah, et al.
Veröffentlicht: (2024)

Learning Concept-Driven Logical Rules for Interpretable and Generalizable Medical Image Classification
von: Gao, Yibo, et al.
Veröffentlicht: (2025)

Image Classification with Deep Reinforcement Active Learning
von: Jiu, Mingyuan, et al.
Veröffentlicht: (2024)

TTRV: Test-Time Reinforcement Learning for Vision Language Models
von: Singh, Akshit, et al.
Veröffentlicht: (2025)

GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification
von: Bakkali, Souhail, et al.
Veröffentlicht: (2023)

Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models
von: Cao, Sihan, et al.
Veröffentlicht: (2026)

Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models
von: Atabuzzaman, Md., et al.
Veröffentlicht: (2025)

TransMed: Large Language Models Enhance Vision Transformer for Biomedical Image Classification
von: Zheng, Kaipeng, et al.
Veröffentlicht: (2023)

Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning
von: Deng, Huilin, et al.
Veröffentlicht: (2025)

Degradation-Aware Image Enhancement via Vision-Language Classification
von: Cai, Jie, et al.
Veröffentlicht: (2025)

OpenPath: Open-Set Active Learning for Pathology Image Classification via Pre-trained Vision-Language Models
von: Zhong, Lanfeng, et al.
Veröffentlicht: (2025)

Multi-View Synergistic Learning with Vision-Language Adaption for Low-Resource Biomedical Image Classification
von: Luo, Xiaoliu, et al.
Veröffentlicht: (2026)

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
von: Li, Ling, et al.
Veröffentlicht: (2025)

Enhancing Fine-Grained Image Classifications via Cascaded Vision Language Models
von: Wei, Canshi
Veröffentlicht: (2024)

A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model
von: Hu, Panwen, et al.
Veröffentlicht: (2024)

Few-Shot Image Classification and Segmentation as Visual Question Answering Using Vision-Language Models
von: Meng, Tian, et al.
Veröffentlicht: (2024)

Vision-Language Model Based Multi-Expert Fusion for CT Image Classification
von: Bai, Jianfa, et al.
Veröffentlicht: (2026)

DocVCE: Diffusion-based Visual Counterfactual Explanations for Document Image Classification
von: Saifullah, Saifullah, et al.
Veröffentlicht: (2025)

ReCAD: Reinforcement Learning Enhanced Parametric CAD Model Generation with Vision-Language Models
von: Li, Jiahao, et al.
Veröffentlicht: (2025)

Hierarchical Vision Transformer with Prototypes for Interpretable Medical Image Classification
von: Gallée, Luisa, et al.
Veröffentlicht: (2025)

MIRL: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
von: Zhang, Yin, et al.
Veröffentlicht: (2026)

Small Language Model Meets with Reinforced Vision Vocabulary
von: Wei, Haoran, et al.
Veröffentlicht: (2024)

Reinforcement Learning Friendly Vision-Language Model for Minecraft
von: Jiang, Haobin, et al.
Veröffentlicht: (2023)

Cropper: Vision-Language Model for Image Cropping through In-Context Learning
von: Lee, Seung Hyun, et al.
Veröffentlicht: (2024)

Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
von: Lai, Yuxiang, et al.
Veröffentlicht: (2025)

Intersectional Fairness in Vision-Language Models for Medical Image Disease Classification
von: Zhang, Yupeng, et al.
Veröffentlicht: (2025)

ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification
von: Shi, Jiangbo, et al.
Veröffentlicht: (2025)

ZeroSlide: Is Zero-Shot Classification Adequate for Lifelong Learning in Whole-Slide Image Analysis in the Era of Pathology Vision-Language Foundation Models?
von: Bui, Doanh C., et al.
Veröffentlicht: (2025)

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

Accelerating Conditional Prompt Learning via Masked Image Modeling for Vision-Language Models
von: Bui, Phuoc-Nguyen, et al.
Veröffentlicht: (2025)

Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification
von: Mahbod, Amirreza, et al.
Veröffentlicht: (2025)

G1: Bootstrapping Perception and Reasoning Abilities of Vision-Language Model via Reinforcement Learning
von: Chen, Liang, et al.
Veröffentlicht: (2025)