A Japanese document parsing model built from Nemotron-3-Nano-Omni, trained with mixed SFT and DAPO reinforcement learning, reaches 87.67 on a synthetic Japanese document parsing benchmark.
OmniDocBench: Benchmarking diverse PDF document parsing with comprehensive annotations
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Stockmark-Nemotron-3-Nano-Omni-JapanDocReader: Structured Document Parsing via Capability Injection and Forgetting Control
A Japanese document parsing model built from Nemotron-3-Nano-Omni, trained with mixed SFT and DAPO reinforcement learning, reaches 87.67 on a synthetic Japanese document parsing benchmark.