OXR 文档解析模型发布，将解析失败纳入训练过程
OXR 成为首个在后训练阶段使用 RSI 的文档解析器：由 VLM 评估输出、rollout 分歧标记不确定性、聚类模型归因，再据此指导下一轮定向数据生成。产出的 1.3B 模型在 olmOCR-Bench、OmniDocBench 和 DocParsingBench 上排名第一，在单张 RTX PRO 6000 上吞吐达 GLM-OCR 的 3.05×，是速度对比中最快的开源结果。
OXR makes parsing failures part of the training process.
During post-training (OXR is the first document parser to use RSI here), a VLM evaluates its outputs, rollout disagreements flag uncertainty, and a separate clustering model groups the causes;
those findings then guide targeted data generation for the next round, and the 1.3B model that comes out of it sits first on olmOCR-Bench, OmniDocBench and DocParsingBench while running 3.05× GLM-OCR's throughput on a single RTX PRO 6000, the fastest open-source result in the speed comparison.
Worth studying (Github link in comment)
来源：rohanpaul_ai · x.com