PaDoc: Layout-Grounded Parallel Decoding for Document Parsing
Quick summary
arXiv:2608.06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formulation forces independent regions onto a decoding path whose length grows with the total content, whereas crop-based two-stage parsers expose region-level parallelism at the cost of repeated visual prefills and fragmented page context. To retain full-page context while removing dependencies, we propose PaDoc, a layout-grounded parser that treats the predicted layout as a branching structure over a s
Key takeaways
- arXiv:2608.06146v1 Announce Type: new Abstract: End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence.
- This formulation forces independent regions onto a decoding path whose length grows with the total content, whereas crop-based two-stage parsers expose region-level parallelism at the cost of repeated visual prefills and fragmented page context.
- To retain full-page context while removing dependencies, we propose PaDoc, a layout-grounded parser that treats the predicted layout as a branching structure over a s
Why it matters
“PaDoc: Layout-Grounded Parallel Decoding for Document Parsing” illustrates how changes in the AI ecosystem can affect products, workflows and user expectations together. Its lasting significance depends on measurable adoption, cost and safety outcomes.
Member comments