AI RESEARCH
HSD: Training-Free Acceleration for Document Parsing Vision-Language Model with Hierarchical Speculative Decoding
arXiv CS.CV
•
ArXi:2602.12957v2 Announce Type: replace Document parsing is a fundamental task in multimodal understanding, ing a wide range of downstream applications such as information extraction and intelligent document analysis. Benefiting from strong semantic modeling and robust generalization, VLM-based end-to-end approaches have emerged as the mainstream paradigm in recent years. However, these models often suffer from substantial inference latency, as they must autoregressively generate long, full-page sequences when processing long-form documents.