{"total":116,"rows":[{"id":"2510.14528","title":"PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model","created":"2025-10-16","cited_by_count":89,"area":"mllm"},{"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":"2601.21821","title":"MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods","created":"2026-01-29","cited_by_count":30,"area":"lr"},{"id":"2603.25040","title":"Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale","created":"2026-03-26","cited_by_count":29,"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":"2601.23265","title":"PaperBanana: Automating Academic Illustration for AI Scientists","created":"2026-01-30","cited_by_count":26,"area":null},{"id":"2603.10910","title":"GLM-OCR Technical Report","created":"2026-03-11","cited_by_count":26,"area":null},{"id":"2512.16676","title":"DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI","created":"2025-12-18","cited_by_count":23,"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":"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":"2511.22850","title":"Resolving Evidence Sparsity: Agentic Context Engineering for Long-Document Understanding","created":"2025-11-28","cited_by_count":18,"area":"agents"},{"id":"2512.04987","title":"Nex-N1: Agentic Models Trained via a Unified Ecosystem for Large-Scale Environment Construction","created":"2025-12-04","cited_by_count":17,"area":"agents"},{"id":"2511.11552","title":"DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding","created":"2025-11-14","cited_by_count":15,"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":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"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":"2602.13318","title":"DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing","created":"2026-02-10","cited_by_count":11,"area":null},{"id":"2601.13606","title":"ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch","created":"2026-01-20","cited_by_count":10,"area":"lr"},{"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":"2511.18434","title":"DocPTBench: Benchmarking End-to-End Photographed Document Parsing and Translation","created":"2025-11-23","cited_by_count":9,"area":"mllm"},{"id":"2512.02895","title":"MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm","created":"2025-12-02","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":"2603.22458","title":"MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2604.10167","title":"Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval","created":"2026-04-11","cited_by_count":8,"area":null},{"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":"2512.10619","title":"DOCR-Inspector: Fine-Grained and Automated Evaluation of Document Parsing with VLM","created":"2025-12-11","cited_by_count":6,"area":null},{"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":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"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":"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":"2605.12882","title":"CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence","created":"2026-05-13","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":"2603.01666","title":"Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations","created":"2026-03-02","cited_by_count":4,"area":null},{"id":"2603.23896","title":"MMTIT-Bench: A Multilingual and Multi-Scenario Benchmark with Cognition-Perception-Reasoning Guided Text-Image Machine Translation","created":"2026-03-25","cited_by_count":4,"area":null},{"id":"2604.16909","title":"PRISM: Probing Reasoning, Instruction, and Source Memory in LLM Hallucinations","created":"2026-04-18","cited_by_count":4,"area":"lr"},{"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":"2605.30794","title":"MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing Understanding","created":"2026-05-29","cited_by_count":4,"area":"mllm"},{"id":"2607.07836","title":"Infinity-Parser2 Technical Report","created":"2026-07-08","cited_by_count":4,"area":"lr"},{"id":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2603.00805","title":"NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code","created":"2026-02-28","cited_by_count":3,"area":"agents"},{"id":"2603.13224","title":"Visual-ERM: Reward Modeling for Visual Equivalence","created":"2026-03-13","cited_by_count":3,"area":"alignment"},{"id":"2603.24326","title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","created":"2026-03-25","cited_by_count":3,"area":"mllm"},{"id":"2604.21510","title":"OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving","created":"2026-04-23","cited_by_count":3,"area":"lr"},{"id":"2605.01345","title":"The Perceptual Bandwidth Bottleneck in Vision-Language Models: Active Visual Reasoning via Sequential Experimental Design","created":"2026-05-02","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":"2511.19945","title":"Low-Resolution Editing is All You Need for High-Resolution Editing","created":"2025-11-25","cited_by_count":2,"area":null},{"id":"2601.14490","title":"GutenOCR: A Grounded Vision-Language Front-End for Documents","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2603.01121","title":"HVR-Met: A Hypothesis-Verification-Replanning Agentic System for Extreme Weather Diagnosis","created":"2026-03-01","cited_by_count":2,"area":"agents"},{"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":"2603.12249","title":"SciMDR: Advancing Scientific Multimodal Document Reasoning","created":"2026-03-12","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":"2605.09635","title":"K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs","created":"2026-05-10","cited_by_count":2,"area":null},{"id":"2605.23694","title":"ChartFI: Benchmarking Faithfulness and Insightfulness of Chart Descriptions from Multimodal Large Language Models","created":"2026-05-22","cited_by_count":2,"area":"mllm"},{"id":"2606.03054","title":"ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents","created":"2026-06-02","cited_by_count":2,"area":"agents"},{"id":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2601.07483","title":"FocalOrder: Focal Preference Optimization for Reading Order Detection","created":"2026-01-12","cited_by_count":1,"area":"alignment"},{"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":"2605.02392","title":"Is It Novel and Why? Fine-Grained Patent Novelty Prediction Based on Passage Retrieval","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2605.17356","title":"UniPPTBench: A Unified Benchmark for Presentation Generation Across Diverse Input Settings","created":"2026-05-17","cited_by_count":1,"area":null},{"id":"2605.22100","title":"MPDocBench-Parse: Benchmarking Practical Multi-page Document Parsing","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2608.03525","title":"MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition","created":"2026-08-04","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":"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":"2609.24058","title":"All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts","created":"2026-09-21","cited_by_count":1,"area":"moe"},{"id":"2511.16216","title":"FlipVQA: Scaling Multi-modal Instruction Tuning via Textbook-to-Knowledge Synthesis","created":"2025-11-20","cited_by_count":0,"area":null},{"id":"2602.06402","title":"MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing","created":"2026-02-06","cited_by_count":0,"area":"mllm"},{"id":"2602.10881","title":"Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.09231","title":"Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness","created":"2026-03-10","cited_by_count":0,"area":"synth"},{"id":"2603.27694","title":"Can Large Language Models Simulate Human Cognition Beyond Behavioral Imitation?","created":"2026-03-29","cited_by_count":0,"area":"lr"},{"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":"2604.02794","title":"CharTool: Tool-Integrated Visual Reasoning for Chart Understanding","created":"2026-04-03","cited_by_count":0,"area":"lr"},{"id":"2604.14967","title":"UniDoc-RL: Coarse-to-Fine Visual RAG with Hierarchical Actions and Dense Rewards","created":"2026-04-16","cited_by_count":0,"area":"mllm"},{"id":"2605.00911","title":"When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation","created":"2026-04-29","cited_by_count":0,"area":"rag"},{"id":"2605.08421","title":"Beyond Bag-of-Patches: Learning Global Layout via Textual Supervision for Late-Interaction Visual Document Retrieval","created":"2026-05-08","cited_by_count":0,"area":null},{"id":"2606.09435","title":"MUDIDI: A Two-Stage Framework for Multilingual Dictionary Digitization with Language Models","created":"2026-06-08","cited_by_count":0,"area":"mllm"},{"id":"2607.18839","title":"HPD-Parsing: Hierarchical Parallel Document Parsing","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2607.24707","title":"ERUnderstand: Evaluating Vision-Language Models on Structured ER Diagrams","created":"2026-07-27","cited_by_count":0,"area":"mllm"},{"id":"2608.00536","title":"DocPO: Advancing Document Policy Optimization via Tailored Step-Aware Rewards","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.07527","title":"DocAtlas: Long-Document Understanding as Mutable-State Interaction","created":"2026-07-21","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":"2608.07943","title":"Locating Failure in Multi-Page Visually Rich Document Understanding: An Empirical Attribution","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.09842","title":"From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing","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":"2608.16628","title":"Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2608.17550","title":"Code as Representation: A Compilable Parsing Paradigm for Academic Documents","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.22959","title":"WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans","created":"2026-08-24","cited_by_count":0,"area":null}],"next_cursor":"100"}