{"total":71,"rows":[{"id":"2512.07584","title":"LongCat-Image Technical Report","created":"2025-12-08","cited_by_count":100,"area":null},{"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":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"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":"2512.17650","title":"Region-Constraint In-Context Generation for Instructional Video Editing","created":"2025-12-19","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":"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":"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":"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":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"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":"2602.12127","title":"PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback","created":"2026-02-12","cited_by_count":9,"area":null},{"id":"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":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"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":"2512.09874","title":"Benchmarking Document Parsers on Mathematical Formula Extraction from PDFs","created":"2025-12-10","cited_by_count":4,"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":"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":"2510.03570","title":"Evaluating OCR performance on food packaging labels in South Africa","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2511.23071","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":"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":"2604.06160","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":"2606.24484","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":"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":"2511.20478","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":"2603.27365","title":"Falcon Perception","created":"2026-03-28","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":"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":"2511.20854","title":"Unsupervised Memorability Modeling from Tip-of-the-Tongue Retrieval Queries","created":"2025-11-25","cited_by_count":0,"area":null},{"id":"2511.23115","title":"Analyzing Image Beyond Visual Aspect: Image Emotion Classification via Multiple-Affective Captioning","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2511.23355","title":"A Hierarchical Computer Vision Pipeline for Physiological Data Extraction from Bedside Monitors","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2602.02223","title":"Evaluating OCR Performance for Assistive Technology: Effects of Walking Speed, Camera Placement, and Camera Type","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2604.23814","title":"Mapping License Plate Recoverability Under Extreme Viewing Angles for Opportunistic Urban Sensing","created":"2026-04-26","cited_by_count":0,"area":null},{"id":"2606.07401","title":"RealDocBench: A Benchmark for Field-Level QA and Layout Understanding on Real-World Regulated Documents","created":"2026-06-05","cited_by_count":0,"area":null},{"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":"2606.18782","title":"RedactionBench","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2607.14682","title":"Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.17849","title":"AlphaOracle: Oracle bone script decipherment via human-workflow-inspired deep learning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.23886","title":"Harnessing X-ray Absorption Spectroscopy Data through Multimodal Mining of Battery Literature","created":"2026-07-26","cited_by_count":0,"area":null},{"id":"2608.06062","title":"Bar-JEPA: Extracting Values from Bar Chart with Joint-Embedding Predictive Architecture","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.30510","title":"Lot Machine: Multimodal Lot Extraction from Auction Catalogs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.07462","title":"When Superpixels Fail on Documents: A Study of Segmentation for LIME Explanations","created":"2026-09-07","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":"2609.36145","title":"From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36563","title":"AffectReveal: Event-Grounded Emotion Recognition Beyond Visual Appearances","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.37569","title":"Decompose Radicals, Then Reward: Fine-Grained Inspection for Accurate Chinese Text Rendering","created":"2026-09-29","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":"2609.39451","title":"ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image Compression","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.39601","title":"GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40356","title":"ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.09823","title":"UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12363","title":"HANS: A Handwritten Answer Sheet Dataset for Noisy Hybrid Document Parsing","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13301","title":"PAGE: Parts-Aware Guidance for Co-Speech Gesture Portrait Video Generation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.13412","title":"TextVBench: Evaluating Text Rendering and Preservation in Video Generation","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.18284","title":"Efficient Scene-Text Refinement via Pixel-Space Grouped Image Generation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}