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.
Qwen3.6-27B: Flagship-level coding in a 27B dense model
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CL 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 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.