Japanese Handwriting Generation Based on Human Preference Feedback Using Direct Preference Optimization

cs.CV

Submitted: 2026-10-10

Updated: 2026-10-10

Comments: Accepted for publication at BESC 2026

Code: https://github.com/kaonashi-tyc/zi2zi

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Proximal Policy Optimization Algorithms

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models