{"total":143,"rows":[{"id":"2512.07584","title":"LongCat-Image Technical Report","created":"2025-12-08","cited_by_count":100,"area":null},{"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":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"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":"2509.05952","title":"Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching","created":"2025-09-07","cited_by_count":56,"area":"diffusion"},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2512.02498","title":"dots.ocr: Multilingual Document Layout Parsing in a Single Vision-Language Model","created":"2025-12-02","cited_by_count":47,"area":"mllm"},{"id":"2605.12500","title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","created":"2026-05-12","cited_by_count":32,"area":"mllm"},{"id":"2603.09877","title":"InternVL-U: Democratizing Unified Multimodal Models for Understanding, Reasoning, Generation and Editing","created":"2026-03-10","cited_by_count":28,"area":"lr"},{"id":"2605.27365","title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","created":"2026-05-26","cited_by_count":28,"area":"mllm"},{"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":"2512.17650","title":"Region-Constraint In-Context Generation for Instructional Video Editing","created":"2025-12-19","cited_by_count":23,"area":null},{"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":"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":"2510.11026","title":"GIR-Bench: Versatile Benchmark for Generating Images with Reasoning","created":"2025-10-13","cited_by_count":15,"area":"lr"},{"id":"2602.12205","title":"DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing","created":"2026-02-12","cited_by_count":14,"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":"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":"2512.23568","title":"ThinkGen: Generalized Thinking for Visual Generation","created":"2025-12-29","cited_by_count":13,"area":"lr"},{"id":"2603.01840","title":"FireRed-OCR Technical Report","created":"2026-03-02","cited_by_count":13,"area":null},{"id":"2604.20796","title":"LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model","created":"2026-04-22","cited_by_count":13,"area":"diffusion"},{"id":"2509.24709","title":"IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?","created":"2025-09-29","cited_by_count":12,"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":"2602.01382","title":"PromptRL: Prompt Matters in RL for Flow-Based Image Generation","created":"2026-02-01","cited_by_count":12,"area":"diffusion"},{"id":"2602.14974","title":"DM0: An Embodied-Native Vision-Language-Action Model towards Physical AI","created":"2026-02-16","cited_by_count":12,"area":"vla"},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"id":"2508.13238","title":"DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model","created":"2025-08-18","cited_by_count":10,"area":"lr"},{"id":"2601.09487","title":"SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics","created":"2026-01-14","cited_by_count":10,"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":"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":"2601.08834","title":"Reading or Reasoning? Format Decoupled Reinforcement Learning for Document OCR","created":"2025-12-11","cited_by_count":9,"area":null},{"id":"2602.06422","title":"Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO","created":"2026-02-06","cited_by_count":9,"area":"lr"},{"id":"2602.12127","title":"PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback","created":"2026-02-12","cited_by_count":9,"area":null},{"id":"2510.20812","title":"Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation","created":"2025-10-23","cited_by_count":8,"area":"lr"},{"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":"2509.18189","title":"Qianfan-VL: Domain-Enhanced Universal Vision-Language Models","created":"2025-09-19","cited_by_count":7,"area":"mllm"},{"id":"2511.14446","title":"Agentic Video Intelligence: A Flexible Framework for Advanced Video Exploration and Understanding","created":"2025-11-18","cited_by_count":7,"area":"agents"},{"id":"2511.20651","title":"RubricRL: Simple Generalizable Rewards for Text-to-Image Generation","created":"2025-11-25","cited_by_count":7,"area":"alignment"},{"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":"2604.23380","title":"V-GRPO: Online Reinforcement Learning for Denoising Generative Models Is Easier than You Think","created":"2026-04-25","cited_by_count":7,"area":"lr"},{"id":"2509.18776","title":"AECBench: A Hierarchical Benchmark for Knowledge Evaluation of Large Language Models in the AEC Field","created":"2025-09-23","cited_by_count":6,"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":"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":"2511.10552","title":"URaG: Unified Retrieval and Generation in Multimodal LLMs for Efficient Long Document Understanding","created":"2025-11-13","cited_by_count":5,"area":"mllm"},{"id":"2512.13303","title":"ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement","created":"2025-12-15","cited_by_count":5,"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":"2604.28185","title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","created":"2026-04-30","cited_by_count":5,"area":"wm"},{"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":"2601.17340","title":"TEXTS-Diff: TEXTS-Aware Diffusion Model for Real-World Text Image Super-Resolution","created":"2026-01-24","cited_by_count":4,"area":"diffusion"},{"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":"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":"2605.06376","title":"Continuous-Time Distribution Matching for Few-Step Diffusion Distillation","created":"2026-05-07","cited_by_count":4,"area":"diffusion"},{"id":"2607.24731","title":"Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation","created":"2026-07-27","cited_by_count":4,"area":"diffusion"},{"id":"2509.11662","title":"MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs","created":"2025-09-15","cited_by_count":3,"area":"mllm"},{"id":"2510.26114","title":"OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2512.15098","title":"Uni-Parser Technical Report","created":"2025-12-17","cited_by_count":3,"area":null},{"id":"2602.21956","title":"Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation","created":"2026-02-25","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":"2604.07419","title":"ReAlign: Optimizing the Visual Document Retriever with Reasoning-Guided Fine-Grained Alignment","created":"2026-04-08","cited_by_count":3,"area":"lr"},{"id":"2606.11977","title":"ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction","created":"2026-06-10","cited_by_count":3,"area":"agents"},{"id":"2606.23254","title":"SteerVTE: Seamless Video Text Editing with Style and Glyph Control","created":"2026-06-22","cited_by_count":3,"area":"diffusion"},{"id":"2510.03570","title":"Evaluating OCR performance on food packaging labels in South Africa","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2511.11313","title":"DocSLM: A Small Vision-Language Model for Long Multimodal Document Understanding","created":"2025-11-14","cited_by_count":2,"area":"lr"},{"id":"2511.23071","title":"Bharat Scene Text: A Novel Comprehensive Dataset and Benchmark for Indian Language Scene Text Understanding","created":"2025-11-28","cited_by_count":2,"area":null},{"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":"2512.17221","title":"DAVE: A VLM Vision Encoder for Document Understanding and Web Agents","created":"2025-12-19","cited_by_count":2,"area":"mllm"},{"id":"2603.00918","title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","created":"2026-03-01","cited_by_count":2,"area":"alignment"},{"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":"2604.00270","title":"OmniSch: A Multimodal PCB Schematic Benchmark For Structured Diagram Visual Reasoning","created":"2026-03-31","cited_by_count":2,"area":"lr"},{"id":"2604.06160","title":"The Character Error Vector: Decomposable errors for page-level OCR evaluation","created":"2026-04-07","cited_by_count":2,"area":null},{"id":"2606.10640","title":"ChartLens: A Dual-Branch Framework for Chart Data Correction and Factual Summary Refinement","created":"2026-06-09","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":"2606.29905","title":"StrucTab: A Structured Optimization Framework for Table Parsing","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2510.21501","title":"GranViT: A Fine-Grained Vision Model With Autoregressive Perception For MLLMs","created":"2025-10-23","cited_by_count":1,"area":"mllm"},{"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":"2511.17106","title":"ChainV: Atomic Visual Hints Make Multimodal Reasoning Shorter and Better","created":"2025-11-21","cited_by_count":1,"area":"lr"},{"id":"2511.20478","title":"NVIDIA Nemotron Parse 1.1","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.14758","title":"The Renaissance of Expert Systems: Optical Recognition of Printed Chinese Jianpu Musical Scores with Lyrics","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.08749","title":"Shifting the Breaking Point of Flow Matching for Multi-Instance Editing","created":"2026-02-09","cited_by_count":1,"area":"diffusion"},{"id":"2603.00707","title":"Towards Khmer Scene Document Layout Detection","created":"2026-02-28","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":"2604.21396","title":"VG-CoT: Towards Trustworthy Visual Reasoning via Grounded Chain-of-Thought","created":"2026-04-23","cited_by_count":1,"area":"lr"},{"id":"2605.13027","title":"PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution","created":"2026-05-13","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":"2607.02290","title":"DisciplineGen-1M: A Large-Scale Dataset for Multidisciplinary Visual Generation and Editing","created":"2026-07-02","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":"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":"2511.20854","title":"Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries","created":"2025-11-25","cited_by_count":0,"area":null}],"next_cursor":"100"}