{"total":183,"rows":[{"id":"2512.13564","title":"Memory in the Age of AI Agents","created":"2025-12-15","cited_by_count":303,"area":"agents"},{"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":"2511.04570","title":"Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm","created":"2025-11-06","cited_by_count":42,"area":"lr"},{"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":"2511.15065","title":"Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks","created":"2025-11-19","cited_by_count":22,"area":"lr"},{"id":"2601.04786","title":"AgentOCR: Reimagining Agent History via Optical Self-Compression","created":"2026-01-08","cited_by_count":22,"area":"agents"},{"id":"2602.05384","title":"Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting","created":"2026-02-05","cited_by_count":22,"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":"2511.19575","title":"HunyuanOCR Technical Report","created":"2025-11-24","cited_by_count":20,"area":"mllm"},{"id":"2511.15244","title":"Context Cascade Compression: Exploring the Upper Limits of Text Compression","created":"2025-11-19","cited_by_count":17,"area":null},{"id":"2601.21468","title":"MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoning","created":"2026-01-29","cited_by_count":15,"area":"agents"},{"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":"2602.15329","title":"EventMemAgent: Hierarchical Event-Centric Memory for Online Video Understanding with Adaptive Tool Use","created":"2026-02-17","cited_by_count":12,"area":null},{"id":"2603.15634","title":"NextMem: Towards Latent Factual Memory for LLM-based Agents","created":"2026-02-26","cited_by_count":12,"area":"agents"},{"id":"2512.15649","title":"VTCBench: Can Vision-Language Models Understand Long Context with Vision-Text Compression?","created":"2025-12-17","cited_by_count":11,"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":"2601.23184","title":"ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought","created":"2026-01-30","cited_by_count":10,"area":"lr"},{"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":"2601.22069","title":"VTC-R1: Vision-Text Compression for Efficient Long-Context Reasoning","created":"2026-01-29","cited_by_count":8,"area":"lr"},{"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":"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":"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":"2512.02337","title":"SpecPV: Improving Self-Speculative Decoding for Long-Context Generation via Partial Verification","created":"2025-12-02","cited_by_count":7,"area":"inference"},{"id":"2512.08923","title":"Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs","created":"2025-12-09","cited_by_count":7,"area":"mllm"},{"id":"2602.05014","title":"DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Search","created":"2026-02-04","cited_by_count":7,"area":"lr"},{"id":"2602.06566","title":"SPARC: Separating Perception And Reasoning Circuits for Test-time Scaling of VLMs","created":"2026-02-06","cited_by_count":7,"area":"lr"},{"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":"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":"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":"2604.06912","title":"Q-Zoom: Query-Aware Adaptive Perception for Efficient Multimodal Large Language Models","created":"2026-04-08","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":"2512.05853","title":"VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack","created":"2025-12-05","cited_by_count":5,"area":"lr"},{"id":"2602.02092","title":"FSVideo: Fast Speed Video Diffusion Model in a Highly-Compressed Latent Space","created":"2026-02-02","cited_by_count":5,"area":"diffusion"},{"id":"2602.13758","title":"OmniScience: A Large-scale Multi-modal Dataset for Scientific Image Understanding","created":"2026-02-14","cited_by_count":5,"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":"2603.25681","title":"Self-Improvement of Large Language Models: A Technical Overview and Future Outlook","created":"2026-03-26","cited_by_count":5,"area":"synth"},{"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":"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":"2512.01822","title":"InnoGym: Benchmarking the Innovation Potential of AI Agents","created":"2025-12-01","cited_by_count":4,"area":"lr"},{"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":"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":"2605.24456","title":"EgoProx: Evaluating MLLMs on Egocentric 3D Proximity Reasoning Across a Cognitive Hierarchy","created":"2026-05-23","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":"2607.11562","title":"MonkeyOCRv2: A Visual-Text Foundation Model for Document AI","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2512.14177","title":"Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes","created":"2025-12-16","cited_by_count":3,"area":"mllm"},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2601.04519","title":"TokenSeg: Efficient 3D Medical Image Segmentation via Hierarchical Visual Token Compression","created":"2026-01-08","cited_by_count":3,"area":null},{"id":"2602.04289","title":"Proxy Compression for Language Modeling","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2602.10146","title":"VERA: Identifying and Leveraging Visual Evidence Retrieval Heads in Long-Context Understanding","created":"2026-02-09","cited_by_count":3,"area":"mllm"},{"id":"2603.20366","title":"WebNavigator: Global Web Navigation via Interaction Graph Retrieval","created":"2026-03-20","cited_by_count":3,"area":null},{"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":"2604.17295","title":"LLaTiSA: Towards Difficulty-Stratified Time Series Reasoning from Visual Perception to Semantics","created":"2026-04-19","cited_by_count":3,"area":"lr"},{"id":"2605.03804","title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"id":"2608.15962","title":"SEER: Long-Context Reasoning via Selective Visual-Text Compression","created":"2026-08-16","cited_by_count":3,"area":"lr"},{"id":"2512.10888","title":"PubTables-v2: A new large-scale dataset for full-page and multi-page table extraction","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2601.14440","title":"VisTIRA: Closing the Image-Text Modality Gap in Visual Math Reasoning via Structured Tool Integration","created":"2026-01-20","cited_by_count":2,"area":"lr"},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","cited_by_count":2,"area":null},{"id":"2602.00454","title":"Cross-Modal Memory Compression for Efficient Multi-Agent Debate","created":"2026-01-31","cited_by_count":2,"area":"agents"},{"id":"2602.16872","title":"DODO: Discrete OCR Diffusion Models","created":"2026-02-18","cited_by_count":2,"area":"diffusion"},{"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":"2603.18652","title":"Beyond String Matching: Semantic Evaluation of PDF Table Extraction","created":"2026-03-19","cited_by_count":2,"area":null},{"id":"2604.04372","title":"Graph-to-Frame RAG: Visual-Space Knowledge Fusion for Training-Free and Auditable Video Reasoning","created":"2026-04-06","cited_by_count":2,"area":"mllm"},{"id":"2604.08216","title":"MemCoT: Test-Time Scaling through Memory-Driven Chain-of-Thought","created":"2026-04-09","cited_by_count":2,"area":"lr"},{"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":"2605.29815","title":"PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.24484","title":"Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2606.28344","title":"PIXELRAG: Web Screenshots Beat Text for Retrieval-Augmented Generation","created":"2026-06-01","cited_by_count":2,"area":"rag"},{"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":"2607.02956","title":"MORE: A Multilingual Document Parsing Benchmark and Evaluation","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2608.01848","title":"Decoupling semantics from vision: A framework for faithful visual-text compression evaluation","created":"2026-08-03","cited_by_count":2,"area":"inference"},{"id":"2511.10618","title":"Know Your Limits: Entropy Estimation Modeling for Compression and Generalization","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2511.20478","title":"NVIDIA Nemotron Parse 1.1","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2601.00561","title":"AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2601.21157","title":"Bridging the Arithmetic Gap: The Cognitive Complexity Benchmark and Financial-PoT for Robust Financial Reasoning","created":"2026-01-29","cited_by_count":1,"area":"lr"},{"id":"2601.22055","title":"$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA","created":"2026-01-29","cited_by_count":1,"area":"rag"},{"id":"2602.02238","title":"Geometry- and Relation-Aware Diffusion for EEG Super-Resolution","created":"2026-02-02","cited_by_count":1,"area":"diffusion"},{"id":"2602.04246","title":"CoLT: Reasoning with Chain of Latent Tool Calls","created":"2026-02-04","cited_by_count":1,"area":"lr"},{"id":"2602.22285","title":"Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning","created":"2026-02-25","cited_by_count":1,"area":null},{"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":"2603.22819","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":"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":"2604.03044","title":"JoyAI-LLM Flash: Advancing Mid-Scale LLMs with Token Efficiency","created":"2026-04-03","cited_by_count":1,"area":"moe"},{"id":"2604.03476","title":"Fine-tuning DeepSeek-OCR-2 for Molecular Structure Recognition","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.04948","title":"From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering","created":"2026-03-30","cited_by_count":1,"area":"rag"},{"id":"2604.12034","title":"Memory as Metabolism: A Design for Companion Knowledge Systems","created":"2026-04-13","cited_by_count":1,"area":"rag"}],"next_cursor":"100"}