cs.CVFeb 23, 2026

NovaLAD: A Fast, CPU-Optimized Document Extraction Pipeline for Generative AI and Data Intelligence

Authors: Aman Ulla

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Document extraction is an important step before retrieval-augmented generation (RAG), knowledge bases, and downstream generative AI can work. It turns unstructured documents like PDFs and scans into structured text and layout-aware representations. We introduce NovaLAD, a comprehensive document parsing system that integrates two concurrent YOLO object detection models - element detection and layout detection - with rule-based grouping and optional vision-language enhancement. When a page image is sent in, the first thing that happens is that it goes through both models at the same time. The element model finds semantic content like the title, header, text, table, image, and so on, and the layout model finds structural regions like layout_box, column_group, multi_column, row_group, and so on. A key design decision is to first send an image or figure through an image classifier (ViT) that decides whether it is relevant or not. Only useful images are then submitted to the Vision LLM for title, summary, and structured information, which cuts down on noise and costs. NovaLAD is built for speed: it works on CPU, employs parallel execution for detection, classification, OCR, and conversion, and generates several forms, including structured JSON, Markdown, RAG-ready texts, and knowledge graphs. We test on the DP-Bench benchmark (upstage/dp-bench) and get 96.49% TEDS and 98.51% NID, which is better than both commercial and open-source parsers. This paper explains how to extract data, how the architecture works, how data flows, and how to make NovaLAD both accurate and usable without needing a GPU.

Figures & tables

Figure 1: Complete end-to-end NovaLAD pipeline. The process begins with a document page fed to parallel Layout Detection and Elements Detection (YOLO models). Images/figures are filtered by a useful vs useless classifier. Layout and filtered elements merge into a unified representation, followed by OCR content extraction. If an LLM is configured, advanced extraction of titles, summaries, and data is performed. The pipeline outputs structured JSON, which is converted to multiple formats (document chunks, Markdown, knowledge graph) with document category classification, culminating in the final NovaLAD output.
MetricValue
Precision0.619
Recall0.530
mAP500.567
mAP50-950.512
Epochs30
Table 1: Layout detection YOLO: final training metrics (epoch 30). Detects layout_box, column_group, multi_column, row_group, etc.
Figure 2: Training and validation dynamics for the layout detection YOLO model. (a) shows how precision, recall, mAP50, and mAP50–95 improve over 30 epochs; (b)–(e) decompose the box, classification, DFL, and objectness losses on train and validation splits; (f) visualizes the learning-rate schedule used during training.
MetricValue
Precision0.806
Recall0.813
mAP500.859
mAP50-950.670
Epochs50
Table 2: Element detection YOLO: final training metrics (epoch 50). Detects title, header, page_header, text, table, image, etc.
Figure 3: Training and validation dynamics for the element detection YOLO model. (a) shows precision, recall, mAP50, and mAP50–95 over 50 epochs; (b)–(e) detail how box, classification, DFL, and objectness losses evolve on train and validation sets; (f) shows the corresponding learning-rate schedule.
BackboneClassifierClassPrecisionRecallF1-scoreAccuracy (%)Time (s)
EfficientNetB0XGBoost00.97020.97430.972297.2217.31
 10.97420.97000.9721
LightGBM00.96770.98150.974597.4322.54
 10.98120.96720.9741
ExtraTrees00.96110.98570.973297.2928.13
 10.98540.96010.9725
Table 3: Performance comparison of different backbones and classifiers for the image usefulness task. Class 0: Useful; Class 1: Useless.
MetricValue
Evaluation
Accuracy98.53%
Loss0.0851
Training
Train loss0.2049
Epochs4
Table 4: Image classifier (ViT): final training and evaluation results. Binary classification: Useful vs Useless.
Figure 4: Training and validation behaviour of the ViT image classifier. Panels (a)–(c) show that loss decreases monotonically while accuracy rises to 98.53%; (d) tracks the gap between training and validation performance, which remains small throughout; (e)–(f) highlight that convergence is fast (4 epochs) and that the final operating point lies in the regime of low validation loss and high accuracy.
SystemTEDS ↑\uparrowNID ↑\uparrowAvg Time (s) ↓\downarrow
NovaLAD ⋆\star96.4998.518.50
Upstage93.4897.023.79
AWS88.0596.7114.47
Microsoft87.1987.694.44
Llamaparse74.5792.824.14
Unstructured65.5691.1813.14
Table 5: DP-Bench results: NovaLAD vs. other parsers. TEDS and NID ↑\uparrow (higher is better); Avg Time ↓\downarrow (lower is better).
Figure 10
Figure 11
Figure 12
Figure 8: Novalad Output post Element and Layout Detection
More in this topic

Document Information Extraction

Document Information Extraction turns text, tables, forms, and images into structured, searchable data.

See all 290 papers

Explore similar work

CardsList
Apr 25, 2026

Lightweight and Production-Ready PDF Visual Element Parsing

PDF documents contain critical visual elements such as figures, tables, and forms whose accurate extraction is essential for document understanding and multimodal retrieval-augmented generation (RAG). Existing PDF parsers often miss complex visuals, extract non-informative artifacts (e.g., watermarks, logos), produce fragmented elements, and fail to reliably associate captions with their corresponding elements, which degrades downstream retrieval and question answering. We present a lightweight and production level PDF parsing framework that can accurately detect visual elements and associates captions using a combination of spatial heuristics, layout analysis, and semantic similarity. On popular benchmark datasets and internal product data, the proposed solution achieves ≥96%\geq96\% visual element detection accuracy and 93%93\% caption association accuracy. When used as a preprocessing step for multimodal RAG, it significantly outperforms state-of-the-art parsers and large vision-language models on both internal data and the MMDocRAG benchmark, while reducing latency by over 2×2\times. We have deployed the proposed system in challenging production environment.

Meizhu Liu, Yassi Abbasi, Matthew Rowe +2

Oracle AI

Document ParsingDocument Layout Analysis
AskPDF
Oct 14, 2026

Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation

Document understanding systems are typically evaluated as separate components via layout analysis, optical text recognition, reading-order prediction, and image captioning. This separation leaves scientific figures, captions, and visual semantics weakly connected, and fails to measure whether a model can produce a single page-level parse that is both structurally faithful and semantically accessible. We introduce Read-Parse-Describe, a unified dataset for document parsing with visual element description generation. Given a page image, models are required to output an ordered list of layout elements containing bounding boxes, semantic labels, reading-order indices, recognized textual content, and alternative text descriptions for visual elements. The benchmark is built from 2,402 documents, comprising 18,163 continuous pages, 125,218 layout elements, and 11,338 visual instances. Besides, we further propose a plug-and-play space-awareness enhancer that reuses multi-layer visual features and injects grid-aware spatial guidance into vision-language tokens for layout-aware generation. Experiments across end-to-end VLMs and pipeline parsers show that existing systems still struggle to jointly recover reading order and visual semantics, while our enhanced model achieves strong joint performance. These results highlight the need to move beyond isolated document parsing modules toward unified models that jointly read, parse, and describe complex documents. The new dataset and code will be made publicly available at https://github.com/yufanchen96/RPD

Yuheng Chen, Yufan Chen, Zhuojun Cai +8

Karlsruhe Institute of Technology · University of Alberta · Hunan University

Document Parsing BenchmarksDocument ParsingDocument Image UnderstandingDocument Layout AnalysisVision-Language Models
AskPDF
Aug 13, 2026

TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents

Document parsing aims to transform unstructured documents into structured and machine-readable representations. Recent advances in Vision-Language Models (VLMs) have significantly advanced document parsing. However, existing approaches still face two major challenges. First, decoupled VLM-based methods heavily rely on accurate layout analysis, where geometric distortions in camera-captured documents can introduce cascading errors. Second, although end-to-end VLM-based methods alleviate the dependence on explicit layout detection, they often suffer from redundant generation, hallucinations, and insufficient structural reasoning in high-resolution scenarios. To address these challenges, we propose TeleOCR, a unified framework for document parsing. TeleOCR introduces deformation-aware learning to incorporate geometric perception into VLMs and proposes an adaptive sampling mechanism for complex layout representation. Furthermore, a content-structure decoupled learning strategy is developed to explicitly model formula grammars and table structures, enabling more effective structured representation learning. Extensive experiments demonstrate that TeleOCR achieves state-of-the-art performance across diverse document parsing benchmarks. It obtains overall scores of 96.87, 88.53 and 78.41 on OmniDocBench v1.6, Wild-OmniDocBench, and PureDocBench, respectively, and ranks first in the ICDAR 2026 Sci-ImageMiner Challenge. These results validate the effectiveness and generalization capability of TeleOCR in complex document parsing scenarios.

Peng Cai, Zhaofan Zou, Shifa Liu +7

China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd.

Vision-Language ModelsDocument ParsingDocument Layout Analysis
AskPDF