{"total":58,"rows":[{"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":"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":"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":"2602.13318","title":"DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing","created":"2026-02-10","cited_by_count":11,"area":null},{"id":"2601.20430","title":"Youtu-Parsing: Perception, Structuring and Recognition via High-Parallelism Decoding","created":"2026-01-28","cited_by_count":10,"area":null},{"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":"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":"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":"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":"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":"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":"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":"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":"2603.11044","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":"2603.15409","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":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","cited_by_count":2,"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":"2603.27365","title":"Falcon Perception","created":"2026-03-28","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":"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":"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":"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":"2602.10881","title":"Diagnosing Structural Failures in LLM-Based Evidence Extraction for Meta-Analysis","created":"2026-02-11","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":"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":"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":"2608.17550","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},{"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":"2609.23592","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":"2609.26381","title":"Layout-Guided Masking for GROBID: Lightweight Structural Gains in Large-Scale Scientific PDF Ingestion","created":"2026-09-22","cited_by_count":0,"area":null},{"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":"2610.09116","title":"SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}