Related papers: LATTE: Improving Latex Recognition for Tables and …
Multi-modal test-time adaptation (MM-TTA) adapts models to an unlabeled target domain by leveraging the complementary multi-modal inputs in an online manner. While previous MM-TTA methods for 3D segmentation offer a promising solution by…
Limited-Angle Computed Tomography (LACT) is a non-destructive evaluation technique used in a variety of applications ranging from security to medicine. The limited angle coverage in LACT is often a dominant source of severe artifacts in the…
Tool learning enables Large Language Models (LLMs) to interact with external environments by invoking tools, serving as an effective strategy to mitigate the limitations inherent in their pre-training data. In this process, tool…
Retrieval-augmented generation (RAG) introduces additional information to enhance large language models (LLMs). In machine translation (MT), previous work typically retrieves in-context examples from paired MT corpora, or domain-specific…
Transfer learning on tabular data is challenging due to disparate feature spaces across domains, in contrast to the homogeneous structures of image and text. Large language models (LLMs) offer a knowledge base to improve the limited…
Img2LaTeX is a practically important task that involves translating mathematical expressions and structured visual content from images into LaTeX code. In recent years, vision-language models (VLMs) have achieved remarkable progress across…
Automated parsing of scanned documents into richly structured, machine-readable formats remains a critical bottleneck in Document AI, as traditional multi-stage pipelines suffer from error propagation and limited adaptability to diverse…
Document reconstruction constitutes a significant facet of document analysis and recognition, a field that has been progressively accruing interest within the scholarly community. A multitude of these researchers employ an array of document…
Recent years have witnessed the rise and success of pre-training techniques in visually-rich document understanding. However, most existing methods lack the systematic mining and utilization of layout-centered knowledge, leading to…
We call on the Document AI (DocAI) community to reevaluate current methodologies and embrace the challenge of creating more practically-oriented benchmarks. Document Understanding Dataset and Evaluation (DUDE) seeks to remediate the halted…
Large Language Models (LLMs) are capable of natural language understanding and generation. But they face challenges such as hallucination and outdated knowledge. Fine-tuning is one possible solution, but it is resource-intensive and must be…
When working to understand usage of a data format, examples of the data format are often more representative than the format's specification. For example, two different applications might use very different JSON representations, or two…
We propose a Makefile for developing containerized $\LaTeX$ technical documents. The Makefile allows the author to execute the code that generates variables, tables and figures (results), which are then used during the $\LaTeX$ compilation,…
Image enhancement aims at improving the aesthetic visual quality of photos by retouching the color and tone, and is an essential technology for professional digital photography. Recent years deep learning-based image enhancement algorithms…
Language models such as GPT and Llama have shown remarkable ability on diverse natural language tasks, yet their performance on complex table tasks (e.g., NL-to-Code and data cleaning) remains suboptimal. Improving performance typically…
Tables have been an ever-existing structure to store data. There exist now different approaches to store tabular data physically. PDFs, images, spreadsheets, and CSVs are leading examples. Being able to parse table structures and extract…
We present the sTeX+ system, a user-driven advancement of sTeX - a semantic extension of LaTeX that allows for producing high-quality PDF documents for (proof)reading and printing, as well as semantic XML/OMDoc documents for the Web or…
Successful Artificial Intelligence systems often require numerous labeled data to extract information from document images. In this paper, we investigate the problem of improving the performance of Artificial Intelligence systems in…
Large language models (LLMs) power deep research agents that synthesize information from hundreds of web sources into cited reports, yet these citations cannot be reliably verified. Current approaches either trust models to self-cite…
Companies regularly spend millions of dollars producing electronically-stored documents in legal matters. Recently, parties on both sides of the 'legal aisle' are accepting the use of machine learning techniques like text classification to…