{"total":74,"rows":[{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"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":"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":"2605.11856","title":"UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal LLMs","created":"2026-05-12","cited_by_count":8,"area":"lr"},{"id":"2606.23050","title":"Unlimited OCR Works","created":"2026-06-22","cited_by_count":8,"area":"inference"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"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":"2603.00479","title":"U-VLM: Hierarchical Vision Language Modeling for Report Generation","created":"2026-02-28","cited_by_count":5,"area":"mllm"},{"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":"2605.27750","title":"Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions","created":"2026-05-26","cited_by_count":5,"area":"mllm"},{"id":"2607.13639","title":"OvisOCR2 Technical Report","created":"2026-07-15","cited_by_count":5,"area":null},{"id":"2602.09003","title":"Data Science and Technology Towards AGI Part I: Tiered Data Management","created":"2026-02-09","cited_by_count":4,"area":null},{"id":"2604.25562","title":"SnapGuard: Lightweight Prompt Injection Detection for Screenshot-Based Web Agents","created":"2026-04-28","cited_by_count":4,"area":"agents"},{"id":"2605.00392","title":"RTPrune: Reading-Twice Inspired Token Pruning for Efficient DeepSeek-OCR Inference","created":"2026-05-01","cited_by_count":4,"area":"inference"},{"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":"2607.07836","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":"2605.08583","title":"Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection","created":"2026-05-09","cited_by_count":3,"area":"agents"},{"id":"2608.23646","title":"MolEmb: Multimodal Large Language Models Can Be Strong Molecular Embedding Models","created":"2026-08-24","cited_by_count":3,"area":"mllm"},{"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":"2606.24447","title":"P-MTP: Efficient Document Parsing via Multi-Token Prediction with Progressive Depth Scaling","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2606.24484","title":"Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2606.29712","title":"Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression","created":"2026-06-29","cited_by_count":2,"area":"lr"},{"id":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","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":"2603.00702","title":"Towards Universal Khmer Text Recognition","created":"2026-02-28","cited_by_count":1,"area":null},{"id":"2603.00707","title":"Towards Khmer Scene Document Layout Detection","created":"2026-02-28","cited_by_count":1,"area":"mllm"},{"id":"2603.13349","title":"MURE: Hierarchical Multi-Resolution Encoding via Vision-Language Models for Visual Document Retrieval","created":"2026-03-07","cited_by_count":1,"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":"2604.03476","title":"Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition","created":"2026-04-03","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":"2605.26712","title":"METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition","created":"2026-05-26","cited_by_count":1,"area":null},{"id":"2606.05736","title":"VTI-CoT: Visual-Textual Interleaved Chain of Thought for Video Reasoning","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.12898","title":"Magnifying What Matters: Attention-Guided Adaptive Rendering for Visual Text Comprehension","created":"2026-06-11","cited_by_count":1,"area":"mllm"},{"id":"2606.13100","title":"LEDGER: A Long-Context Benchmark of Corporate Annual Reports for Grounded Financial Retrieval and Extraction","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2607.22200","title":"LayoutLite: Token-Level Implicit Layout Analysis for Efficient Document OCR","created":"2026-07-24","cited_by_count":1,"area":"mllm"},{"id":"2608.07775","title":"AndroidReality: How Far Are Mobile Agents from the Real World?","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"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":"2603.16245","title":"How to Utilize Complementary Vision-Text Information for 2D Structure Understanding","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.16861","title":"Prefix-Adaptive Block Diffusion for Efficient Document Recognition","created":"2026-05-16","cited_by_count":0,"area":"diffusion"},{"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":"2605.24636","title":"GlobalDentBench: A Multinational Benchmark for Evaluating LLM Clinical Reasoning in Dentistry with Expert Calibration","created":"2026-05-23","cited_by_count":0,"area":"lr"},{"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":"2606.09788","title":"POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.19096","title":"PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction","created":"2026-06-17","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":"2607.18839","title":"HPD-Parsing: Hierarchical Parallel Document Parsing","created":"2026-07-21","cited_by_count":0,"area":"inference"},{"id":"2608.00765","title":"RAGOCR: Optical Compression of Retrieval-Augmented Text via Visual Representation","created":"2026-08-01","cited_by_count":0,"area":"rag"},{"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":"2608.10396","title":"FormStruct-Bench:A Hierarchical and Diagnostic Benchmark for Table-Form Document Structure Recognition","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.12121","title":"QV-PIC: Query-Aware Visual Position-Independent Caching for Efficient RAG Serving","created":"2026-08-12","cited_by_count":0,"area":"rag"},{"id":"2608.16628","title":"Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement","created":"2026-08-17","cited_by_count":0,"area":"rag"},{"id":"2608.22959","title":"WildHandBench: A Benchmark for Handwritten Text Understanding that Challenges MLLMs and Humans","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.27169","title":"Ancient-Bench: A Comprehensive Multi-millennial, Multi-medium, and Multi-script Benchmark for Ancient Chinese Artifact Text Recognition","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2608.28698","title":"State-Conditioned Visual Evidence Retrieval for Fine-Grained Perception in Document Vision-Language Models","created":"2026-08-27","cited_by_count":0,"area":"mllm"},{"id":"2609.01575","title":"Closing Cost-Quality Gap in Document VLMs: Difficulty-Aware Data Curation and Quality-Adjusted Deployment Economics","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.19158","title":"VisKG-LM: Compiling Knowledge Graphs into Visual Memory for Multiple-Choice Question Answering","created":"2026-07-29","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":"2609.21351","title":"PrismAlign: Prior-Steered Multi-View VLM Alignment for Hallucination-Robust Table OCR","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.24092","title":"DocMIDE: Learning Multi-Hop Implicit Derivation in Visually Rich Documents","created":"2026-09-21","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":"2609.31341","title":"The Right Information Extraction Pipeline Depends on the Document: Accuracy-Energy Trade-offs for Small, Local Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.36136","title":"Xiaomi-OCR-0 Technical Report","created":"2026-09-28","cited_by_count":0,"area":"mllm"},{"id":"2609.37311","title":"ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"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":"2610.14531","title":"LongHisDoc: A Comprehensive Benchmark for Chinese Long Historical Document Understanding","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.16956","title":"DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}