Pith. sign in

REVIEW

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.09531 v1 pith:62MP56XO submitted 2025-07-13 cs.CV cs.AIcs.LG

VDInstruct: Zero-Shot Key Information Extraction via Content-Aware Vision Tokenization

classification cs.CV cs.AIcs.LG
keywords tokenizationcontent-awaredocumentsextractionimagemodeltokensvdinstruct
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Key Information Extraction (KIE) underpins the understanding of visual documents (e.g., receipts and contracts) by extracting precise semantic content and accurately capturing spatial structure. Yet existing multimodal large language models (MLLMs) often perform poorly on dense documents and rely on vision tokenization approaches that scale with image size, leading to redundant computation and memory inefficiency. To address these challenges, we introduce VDInstruct, an MLLM that separates spatial region detection from semantic feature extraction. Central to our model is a content-aware tokenization strategy: rather than fragmenting the entire image uniformly, it generates tokens in proportion to document complexity, preserving critical structure while eliminating wasted tokens. Leveraging a three-stage training paradigm, our model achieves state-of-the-art (SOTA) results on KIE benchmarks, matching or exceeding the accuracy of leading approaches while reducing the number of image tokens by roughly 3.6x. In zero-shot evaluations, VDInstruct surpasses strong baselines-such as DocOwl 1.5-by +5.5 F1 points, highlighting its robustness to unseen documents. These findings show that content-aware tokenization combined with explicit layout modeling offers a promising direction forward for document understanding. Data, source code, and model weights will be made publicly available.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.