{"total":76,"rows":[{"id":"2601.20552","title":"DeepSeek-OCR 2: Visual Causal Flow","created":"2026-01-28","cited_by_count":74,"area":null},{"id":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","cited_by_count":57,"area":null},{"id":"2604.04771","title":"MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale","created":"2026-04-06","cited_by_count":27,"area":null},{"id":"2603.10910","title":"GLM-OCR Technical Report","created":"2026-03-11","cited_by_count":26,"area":null},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"id":"2511.15244","title":"Context Cascade Compression: Exploring the Upper Limits of Text Compression","created":"2025-11-19","cited_by_count":17,"area":null},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2512.21095","title":"UniRec-0.1B: Unified Text and Formula Recognition with 0.1B Parameters","created":"2025-12-24","cited_by_count":13,"area":null},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13,"area":null},{"id":"2602.15329","title":"EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2603.28130","title":"MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios","created":"2026-03-30","cited_by_count":5,"area":null},{"id":"2607.13639","title":"OvisOCR2 Technical Report","created":"2026-07-15","cited_by_count":5,"area":null},{"id":"2512.09874","title":"Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2605.07492","title":"How Far Is Document Parsing from Solved? PureDocBench: A Source-Traceable Benchmark across Clean, Degraded, and Real-World Settings","created":"2026-05-08","cited_by_count":4,"area":null},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2601.04519","title":"TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2603.20366","title":"WebNavigator: Global Web Navigation via Interaction Graph Retrieval","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2512.10888","title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2603.15409","title":"SEA-Vision: A Multilingual Benchmark for Comprehensive Document and Scene Text Understanding in Southeast Asia","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.18652","title":"Beyond String Matching: Semantic Evaluation of PDF Table Extraction","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2605.29815","title":"PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.24484","title":"Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2607.02956","title":"MORE: A Multilingual Document Parsing Benchmark and Evaluation","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2511.10618","title":"Know Your Limits: Entropy Estimation Modeling for Compression and Generalization","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2511.20478","title":"NVIDIA Nemotron Parse 1.1","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.00561","title":"AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2602.22285","title":"Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.00702","title":"Towards Universal Khmer Text Recognition","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.22819","title":"TDATR: Improving End-to-End Table Recognition via Table Detail-Aware Learning and Cell-Level Visual Alignment","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.02880","title":"InstructTable: Improving Table Structure Recognition Through Instructions","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.03476","title":"Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2605.15181","title":"From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.26712","title":"METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2607.24077","title":"When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2511.18272","title":"Vision Token Masking Alone Cannot Prevent PHI Leakage in Medical Document OCR: A Systematic Evaluation","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2601.00150","title":"FCMBench: The First Large-scale Financial Credit Multimodal Benchmark for Real-world Applications","created":"2026-01-01","cited_by_count":0,"area":null},{"id":"2601.11248","title":"Language-Agnostic Visual Embeddings for Cross-Script Handwriting Retrieval","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2601.11425","title":"PubMed-OCR: PMC Open Access OCR Annotations","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2602.02014","title":"Rethinking Genomic Modeling Through Optical Character Recognition","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.17189","title":"Texo: Formula Recognition within 20M Parameters","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.19268","title":"Full-Stack Domain Enhancement for Combustion LLMs: Construction and Optimization","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.23976","title":"SilLang: Improving Gait Recognition with Silhouette Language Encoding","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2603.24037","title":"A$^3$: Towards Advertising Aesthetic Assessment","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.02692","title":"Parser-Oriented Structural Refinement for a Stable Layout Interface in Document Parsing","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.27272","title":"When 2D Tasks Meet 1D Serialization: On Serialization Friction in Structured Tasks","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.21611","title":"UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation","created":"2026-05-20","cited_by_count":0,"area":null},{"id":"2606.04479","title":"Evaluating Reasoning Fidelity in Visual Text Generation","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09788","title":"POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.12419","title":"GeoDial: A Multimodal Conversational Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.25329","title":"State Space Models Meet Remote Sensing: A Survey","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2606.28077","title":"TextDS: Parameter-Efficient Representation Alignment for Scene Text Detection under Distribution Shifts","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2606.29378","title":"Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2606.29503","title":"The Verbose Context Problem in Medical Records","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.03650","title":"ClinOCR-Bench: A Comprehensive Clinical Scanned Document Dataset for Optical Character Recognition Model Evaluation","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2608.05911","title":"Mapping Armenian Paris: Extracting and Geocoding Commercial Advertisements from the 20th-Century Diaspora Press","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.07917","title":"TongGuOCR: A Layout-Aware and Token-Augmented OCR MLLM for Chinese Historical Documents","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.12898","title":"TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2608.18696","title":"Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2609.07029","title":"LoGAN: Multilingual Font Localization with Generative Agents","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.20423","title":"WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21018","title":"MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.21543","title":"From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.25715","title":"LingLan: An Advancing Traditional Chinese Medicine Diagnosis LLM with Multimodal Data","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.30682","title":"Structure-Guided Masked Autoencoders for Ultra-High Resolution Scientific Image Understanding","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33447","title":"From PDF to Evidence: Structure-Aware Retrieval for Clinical Practice Guidelines","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.07175","title":"CALR: Continuous Anchored Latent Reasoning via Render-of-Thought Compression","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.10738","title":"Lossy Compressive Text Autoencoders","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12363","title":"HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.20335","title":"Read, Parse, Describe: Unified Document Parsing with Visual Element Description Generation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}