layout-parsing

LightOn 发布新一代轻量级端到端 OCR 模型 LightOnOCR-3 系列，其中 4B 版本采用 Qwen3.5 视觉-语言架构，新增 grounding（带边界框的布局标签）、图像描述和图表数据提取等视觉理解能力，全部以 Apache 2.0 许可开源。

This paper identifies Footprint Bias in document layout analysis robustness evaluation and proposes a structure-aware auditing framework that decouples probe construction and pathway attribution, showing that small structurally targeted probes cause comparable downstream degradation to larger perturbations.