{"total":89,"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":"2510.19817","title":"olmOCR 2: Unit Test Rewards for Document OCR","created":"2025-10-22","cited_by_count":47,"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":"2601.04035","title":"MobileDreamer: Generative Sketch World Model for GUI Agent","created":"2026-01-07","cited_by_count":23,"area":"wm"},{"id":"2601.14251","title":"LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR","created":"2026-01-20","cited_by_count":23,"area":"mllm"},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"area":null},{"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":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"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":"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":"2601.21639","title":"OCRVerse: Towards Holistic OCR in End-to-End Vision-Language Models","created":"2026-01-29","cited_by_count":12,"area":"mllm"},{"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":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"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":"2511.18434","title":"DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation","created":"2025-11-23","cited_by_count":9,"area":"mllm"},{"id":"2601.08834","title":"Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2601.02036","title":"GDRO: Group-level Reward Post-training Suitable for Diffusion Models","created":"2026-01-05","cited_by_count":8,"area":"diffusion"},{"id":"2606.23050","title":"Unlimited OCR Works","created":"2026-06-22","cited_by_count":8,"area":"inference"},{"id":"2602.05014","title":"DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search","created":"2026-02-04","cited_by_count":7,"area":"lr"},{"id":"2603.23885","title":"Towards Real-World Document Parsing via Realistic Scene Synthesis and Document-Aware Training","created":"2026-03-25","cited_by_count":7,"area":"mllm"},{"id":"2511.21750","title":"SO-Bench: A Structural Output Evaluation of Multimodal LLMs","created":"2025-11-23","cited_by_count":6,"area":"mllm"},{"id":"2602.12957","title":"HSD: Training-Free Acceleration for Document Parsing Vision-Language Models with Hierarchical Speculative Decoding","created":"2026-02-13","cited_by_count":6,"area":"mllm"},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"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":"2603.24440","title":"CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents","created":"2026-03-25","cited_by_count":5,"area":"agents"},{"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":"2605.11960","title":"Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters","created":"2026-05-12","cited_by_count":5,"area":null},{"id":"2607.13639","title":"OvisOCR2 Technical Report","created":"2026-07-15","cited_by_count":5,"area":null},{"id":"2512.01248","title":"TRivia: Self-supervised Fine-tuning of Vision-Language Models for Table Recognition","created":"2025-12-01","cited_by_count":4,"area":"mllm"},{"id":"2512.09874","title":"Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2604.08457","title":"CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning","created":"2026-04-09","cited_by_count":4,"area":"lr"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2605.27978","title":"ABot-OCR Technical Report","created":"2026-05-27","cited_by_count":3,"area":"mllm"},{"id":"2606.01911","title":"Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2601.02256","title":"VAR RL Done Right: Tackling Asynchronous Policy Conflicts in Visual Autoregressive Generation","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2602.00122","title":"VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents","created":"2026-01-27","cited_by_count":2,"area":null},{"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":"2603.15206","title":"Efficient Document Parsing via Parallel Token Prediction","created":"2026-03-16","cited_by_count":2,"area":"mllm"},{"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":"2603.25761","title":"A Survey of OCR Evaluation Methods and Metrics and the Invisibility of Historical Documents","created":"2026-03-26","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":"2606.23344","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":"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":"2511.13285","title":"SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2602.11960","title":"Benchmarking Vision-Language Models for French PDF-to-Markdown Conversion","created":"2026-02-12","cited_by_count":1,"area":"mllm"},{"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":"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":"2604.02880","title":"InstructTable: Improving Table Structure Recognition Through Instructions","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.18508","title":"Document-as-Image Representations Fall Short for Scientific Retrieval","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.14894","title":"SEDiT: Mask-Free Video Subtitle Erasure via One-step Diffusion Transformer","created":"2026-05-14","cited_by_count":1,"area":"diffusion"},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.22842","title":"FinixDoc: Rethinking Financial Document Parsing Beyond Saturated Benchmarks","created":"2026-08-24","cited_by_count":1,"area":"lr"},{"id":"2608.28701","title":"TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models","created":"2026-08-27","cited_by_count":1,"area":"lr"},{"id":"2602.11731","title":"Thinking with Drafting: Optical Decompression via Logical Reconstruction","created":"2026-02-12","cited_by_count":0,"area":"lr"},{"id":"2603.20020","title":"Detached Skip-Links and $R$-Probe: Decoupling Feature Aggregation from Gradient Propagation for MLLM OCR","created":"2026-03-20","cited_by_count":0,"area":"lr"},{"id":"2603.27942","title":"JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding","created":"2026-03-30","cited_by_count":0,"area":"mllm"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.22413","title":"From Recognition to Reasoning: Benchmarking and Enhancing MLLMs on Real-World Receipt Document Understanding","created":"2026-05-21","cited_by_count":0,"area":"lr"},{"id":"2606.07401","title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2607.02504","title":"Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas","created":"2026-07-02","cited_by_count":0,"area":"lr"},{"id":"2607.17251","title":"VecFontLLM: Anchor-Guided Direct Synthesis of Chinese Vector Fonts","created":"2026-07-19","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":"2607.27084","title":"SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context","created":"2026-07-29","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":"2608.09536","title":"DocPure: Prompt-Free Unified Document Restoration via Degradation-Aware Structure-Guided Wavelet Modulation","created":"2026-08-10","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":"2608.19739","title":"Question-Guided Evidence Acquisition for Multimodal Visual Question Answering","created":"2026-08-20","cited_by_count":0,"area":"mllm"},{"id":"2609.05535","title":"Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails","created":"2026-09-02","cited_by_count":0,"area":"mllm"},{"id":"2609.07081","title":"SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text Spotting","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.12705","title":"ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts","created":"2026-09-11","cited_by_count":0,"area":"moe"},{"id":"2609.15668","title":"Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic Understanding","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.23592","title":"Collapse, Not Complexity: Failure-Conditioned Decomposition Repair for End-to-End Document Parsing","created":"2026-09-20","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":"2609.37712","title":"PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.11818","title":"From Pixels to Structure: Lightweight Vision-Language Models for Document OCR and Structured JSON Extraction","created":"2026-10-08","cited_by_count":0,"area":"mllm"},{"id":"2610.16784","title":"InfoVis: Unified Slide Image Generation and Editing","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18238","title":"Heading Hierarchy Reconstruction for Complex and Long Documents with Level-Wise Multimodal Memory","created":"2026-10-13","cited_by_count":0,"area":"mllm"},{"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}