structured-document-parsing

Tag

Cards List
#structured-document-parsing

Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control

arXiv cs.CL ↗ · 2026-08-10 Cached

This paper introduces Stockmark-Nemotron-3-Nano-Omni-JapanDocReader, a Japanese document understanding model built by injecting structured document parsing capability into a reasoning-oriented multimodal model while preserving VQA ability. It studies parsing-centric SFT, mixed SFT, and DAPO-based parsing-centric RL to improve structured parsing performance.

0 favorites 0 likes
← Back to home

Submit Feedback