{"total":57,"rows":[{"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":"2603.13398","title":"Qianfan-OCR: A Unified End-to-End Model for Document Intelligence","created":"2026-03-11","cited_by_count":21,"area":"mllm"},{"id":"2606.03264","title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","created":"2026-06-02","cited_by_count":21,"area":null},{"id":"2603.13032","title":"Multimodal OCR: Parse Anything from Documents","created":"2026-03-13","cited_by_count":14,"area":null},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13,"area":null},{"id":"2603.04205","title":"Real5-OmniDocBench: A Full-Scale Physical Reconstruction Benchmark for Robust Document Parsing in the Wild","created":"2026-03-04","cited_by_count":12,"area":"mllm"},{"id":"2605.04128","title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","created":"2026-05-05","cited_by_count":12,"area":null},{"id":"2605.20183","title":"MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation","created":"2026-05-19","cited_by_count":10,"area":null},{"id":"2602.04802","title":"VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?","created":"2026-02-04","cited_by_count":8,"area":"mllm"},{"id":"2602.24134","title":"AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation","created":"2026-02-27","cited_by_count":5,"area":"rag"},{"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":"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":"2605.08888","title":"DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding","created":"2026-05-09","cited_by_count":3,"area":"lr"},{"id":"2605.27978","title":"ABot-OCR Technical Report","created":"2026-05-27","cited_by_count":3,"area":"mllm"},{"id":"2606.11977","title":"ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2607.19064","title":"Mage-Flow: An Efficient Native-Resolution Foundation Model for Image Generation and Editing","created":"2026-07-21","cited_by_count":3,"area":"diffusion"},{"id":"2603.11044","title":"LingDT-VL-OCR: Structure-Aware Document-Level Parsing with Fine-Grained Visual Reference","created":"2026-03-11","cited_by_count":2,"area":null},{"id":"2604.12978","title":"GlotOCR Bench: OCR Models Still Struggle Beyond a Handful of Unicode Scripts","created":"2026-04-14","cited_by_count":2,"area":"mllm"},{"id":"2605.07019","title":"LensVLM: Selective Context Expansion for Compressed Visual Representation of Text","created":"2026-05-07","cited_by_count":2,"area":"mllm"},{"id":"2605.24973","title":"MinerU-Popo: Universal Post-Processing Model for Structured Document Parsing","created":"2026-05-24","cited_by_count":2,"area":null},{"id":"2606.01348","title":"ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2606.06784","title":"What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2606.23344","title":"RT-DocLayout: Real-Time End-to-End Document Layout Analysis with Reading Order in the Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2607.21617","title":"Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language Models","created":"2026-05-29","cited_by_count":2,"area":"mllm"},{"id":"2603.27365","title":"Falcon Perception","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.00161","title":"Q-Mask: Query-driven Causal Masks for Text Anchoring in OCR-Oriented Vision-Language Models","created":"2026-03-31","cited_by_count":1,"area":"mllm"},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2606.08982","title":"Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.19602","title":"Configurable Clinical Information Extraction with Agentic RAG: What Works, What Breaks, and Why","created":"2026-06-17","cited_by_count":1,"area":"rag"},{"id":"2607.21694","title":"Oxygen-TryOn: Fashion-Native Foundation Model for Any-item Virtual Try-On","created":"2026-07-23","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":"2608.06146","title":"PaDoc: Layout-Grounded Parallel Decoding for Document Parsing","created":"2026-08-06","cited_by_count":1,"area":"inference"},{"id":"2608.22842","title":"FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks","created":"2026-08-24","cited_by_count":1,"area":"lr"},{"id":"2608.26592","title":"Benchmarking Clinical Decision Pathway Adherence in Large Language Models","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2609.03445","title":"OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2602.17189","title":"Texo: Formula Recognition within 20M Parameters","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2606.01393","title":"Dr. DocBench: A Comprehensive Benchmark for Expert-Level and Difficult Document Parsing","created":"2026-05-31","cited_by_count":0,"area":"mllm"},{"id":"2606.12830","title":"Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.24118","title":"An LMM for Precisely Grounding Elements in Documents","created":"2026-06-23","cited_by_count":0,"area":"mllm"},{"id":"2606.26041","title":"How Robust is OCR-Reasoning? Evaluating OCR-Reasoning Robustness of Vision-Language Models under Visual Perturbations","created":"2026-06-24","cited_by_count":0,"area":"lr"},{"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":"2607.18839","title":"HPD-Parsing: Hierarchical Parallel Document Parsing","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2608.03292","title":"DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning","created":"2026-08-04","cited_by_count":0,"area":"lr"},{"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":"2608.15064","title":"LongDocBench: Benchmarking TOC Hierarchy and Contextual Relationship Recovery in Long Documents","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2609.00232","title":"Beyond Blind Compliance: Benchmarking Task Verification in OCR Reasoning","created":"2026-08-31","cited_by_count":0,"area":"lr"},{"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":"2609.21351","title":"PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.26638","title":"Diffusion Drafts, AR Verifies: Accelerating Document OCR with Self-Speculative Decoding","created":"2026-09-22","cited_by_count":0,"area":"inference"},{"id":"2609.36136","title":"Xiaomi-OCR-0 Technical Report","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"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}],"next_cursor":null}