{"total":23,"rows":[{"id":"2407.00981","title":"VisEval: A Benchmark for Data Visualization in the Era of Large Language Models","created":"2024-07-01","cited_by_count":45,"area":null},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35,"area":null},{"id":"2403.02253","title":"KnowPhish: Large Language Models Meet Multimodal Knowledge Graphs for Enhancing Reference-Based Phishing Detection","created":"2024-03-04","cited_by_count":33,"area":null},{"id":"2312.07424","title":"How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation","created":"2023-12-12","cited_by_count":22,"area":null},{"id":"2311.12990","title":"NERIF: GPT-4V for Automatic Scoring of Drawn Models","created":"2023-11-21","cited_by_count":13,"area":null},{"id":"2403.04822","title":"UniTable: Towards a Unified Framework for Table Recognition via Self-Supervised Pretraining","created":"2024-03-07","cited_by_count":13,"area":null},{"id":"2312.02694","title":"UPOCR: Towards Unified Pixel-Level OCR Interface","created":"2023-12-05","cited_by_count":12,"area":null},{"id":"2401.00028","title":"An Empirical Study of Scaling Law for OCR","created":"2023-12-29","cited_by_count":7,"area":null},{"id":"2407.13559","title":"Qalam : A Multimodal LLM for Arabic Optical Character and Handwriting Recognition","created":"2024-07-18","cited_by_count":7,"area":null},{"id":"2312.05468","title":"Image and Data Mining in Reticular Chemistry Using GPT-4V","created":"2023-12-09","cited_by_count":6,"area":null},{"id":"2404.09690","title":"Harnessing GPT-4V(ision) for Insurance: A Preliminary Exploration","created":"2024-04-15","cited_by_count":5,"area":null},{"id":"2406.05348","title":"Toward Reliable Ad-hoc Scientific Information Extraction: A Case Study on Two Materials Datasets","created":"2024-06-08","cited_by_count":5,"area":null},{"id":"2401.03472","title":"PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction","created":"2024-01-07","cited_by_count":2,"area":null},{"id":"2403.11468","title":"CollagePrompt: A Benchmark for Budget-Friendly Visual Recognition with GPT-4V","created":"2024-03-18","cited_by_count":2,"area":null},{"id":"2405.02040","title":"Large Multimodal Model based Standardisation of Pathology Reports with Confidence and their Prognostic Significance","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2408.14805","title":"Platypus: A Generalized Specialist Model for Reading Text in Various Forms","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2410.24034","title":"Handwriting Recognition in Historical Documents with Multimodal LLM","created":"2024-10-31","cited_by_count":2,"area":null},{"id":"2407.18716","title":"ChatSchema: A pipeline of extracting structured information with Large Multimodal Models based on schema","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2408.07220","title":"Handwritten Code Recognition for Pen-and-Paper CS Education","created":"2024-08-07","cited_by_count":1,"area":null},{"id":"2410.09729","title":"MIRAGE: Multimodal Identification and Recognition of Annotations in Indian General Prescriptions","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2404.19652","title":"VimTS: A Unified Video and Image Text Spotter for Enhancing the Cross-domain Generalization","created":"2024-04-30","cited_by_count":0,"area":null},{"id":"2509.06246","title":"Exploring Light-Weight Object Recognition for Real-Time Document Detection","created":"2025-09-07","cited_by_count":0,"area":null},{"id":"2512.23454","title":"Automated river gauge plate reading using a hybrid object detection and generative AI framework in the Limpopo River Basin","created":"2025-12-29","cited_by_count":0,"area":null}],"next_cursor":null}