Direct Image-to-Modern Vietnamese Translation of Han-Nom Manuscripts via Multimodal RLHF Preference Alignment

Translating Han-Nom manuscripts into modern Vietnamese is challenging because historical pages are often degraded, the script contains rare logographic characters, and parallel supervision is limited. We propose a multimodal RLHF preference-alignment framework that conditions Vietnamese generation on manuscript images and aligned Han-Nom source text.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• reinforcement-learning
• fine-tuning
• multimodal
• safety