HPD-Parsing: Hierarchical Parallel Document Parsing

Efficient teamwork typically combines global coordination with parallel execution, a principle not yet fully reflected in unified Vision-Language Model (VLM)-based document parsers. Existing unified parsers process an entire page jointly but generate its output through a single token-by-token autoregressive trajectory, creating a sequential bottleneck that grows with document length.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

• llms
• efficiency
• multimodal
• benchmarks