{"total":62,"rows":[{"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":"2511.03929","title":"NVIDIA Nemotron Nano V2 VL","created":"2025-11-06","cited_by_count":17,"area":null},{"id":"2502.16435","title":"Human Cognitive Benchmarks Reveal Foundational Visual Gaps in MLLMs","created":"2025-02-23","cited_by_count":13,"area":null},{"id":"2503.01879","title":"Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And Vision","created":"2025-02-26","cited_by_count":12,"area":null},{"id":"2601.02316","title":"DatBench: Discriminative, Faithful, and Efficient VLM Evaluations","created":"2026-01-05","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":"2507.15085","title":"OCRGenBench: A Comprehensive Benchmark for Evaluating OCR Generative Capabilities","created":"2025-07-20","cited_by_count":9,"area":null},{"id":"2509.19768","title":"CHURRO: Making History Readable with an Open-Weight Large Vision-Language Model for High-Accuracy, Low-Cost Historical Text Recognition","created":"2025-09-24","cited_by_count":9,"area":null},{"id":"2510.15148","title":"XModBench: Benchmarking Cross-Modal Capabilities and Consistency in Omni-Language Models","created":"2025-10-16","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":"2506.01934","title":"RoboEgo System Card: An Omnimodal Model with Native Full Duplexity","created":"2025-06-02","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":"2605.11960","title":"Chronicles-OCR: A Cross-Temporal Perception Benchmark for the Evolutionary Trajectory of Chinese Characters","created":"2026-05-12","cited_by_count":5,"area":null},{"id":"2510.16713","title":"so much depends / upon / a whitespace: Why Whitespace Matters for Poets and LLMs","created":"2025-10-19","cited_by_count":4,"area":null},{"id":"2504.03621","title":"PILOT: A Promptable Interleaved Layout-aware OCR Transformer","created":"2025-04-04","cited_by_count":2,"area":null},{"id":"2510.23477","title":"MMTutorBench: The First Multimodal Benchmark for AI Math Tutoring","created":"2025-10-27","cited_by_count":2,"area":null},{"id":"2602.00122","title":"VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2602.04101","title":"Interfaze: The Future of AI is built on Task-Specific Small Models","created":"2026-02-04","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":"2605.22823","title":"Which Way Did It Move? Diagnosing and Overcoming Directional Motion Blindness in Video-LLMs","created":"2026-05-21","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":"2607.09068","title":"OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents","created":"2026-07-10","cited_by_count":2,"area":null},{"id":"2607.11192","title":"GDP.pdf: Benchmarking Grounded Multimodal Reasoning over Professional PDF Documents","created":"2026-07-13","cited_by_count":2,"area":null},{"id":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2509.03615","title":"E-ARMOR: Edge case Assessment and Review of Multilingual Optical Character Recognition","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2511.04161","title":"Seeing Straight: Document Orientation Detection for Efficient OCR","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2601.02683","title":"Learning from Prompt itself: the Hierarchical Attribution Prompt Optimization","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2603.24078","title":"PosterIQ: A Design Perspective Benchmark for Poster Understanding and Generation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2606.24253","title":"TuringViT: Making SOTA Vision Transformers Accessible to All","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2606.24602","title":"ViTexQA: A Multi-Frame Temporal Perception Dataset for Video Text Question Answering","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2608.08907","title":"ToolVision: Learning When and How to Use Visual Tools with Capability-Aligned Supervision","created":"2026-08-09","cited_by_count":1,"area":null},{"id":"2608.13783","title":"Doomed to Re-Annotate, Forever: The ImageNet Story","created":"2026-08-13","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":"2511.22499","title":"What Shape Is Optimal for Masks in Text Removal?","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2601.09118","title":"LPCAN: Lightweight Pyramid Cross-Attention Network for Rail Surface Defect Detection Using RGB-D Data","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2601.10104","title":"MathDoc: Benchmarking Structured Extraction and Active Refusal on Noisy Mathematics Exam Papers","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2601.20881","title":"MA-LipNet: Multi-Dimensional Attention Networks for Robust Lipreading","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.15903","title":"Detecting Deepfakes with Multivariate Soft Blending and CLIP-based Image-Text Alignment","created":"2026-02-14","cited_by_count":0,"area":null},{"id":"2602.16430","title":"Designing Production-Scale OCR for India: Multilingual and Domain-Specific Systems","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.00118","title":"Efficient Image Super-Resolution with Multi-Scale Spatial Adaptive Attention Networks","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2603.13429","title":"A Deformable Attention-Based Detection Transformer with Cross-Scale Feature Fusion for Industrial Coil Spring Inspection","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.29507","title":"Transmittance-Guided Structure-Texture Decomposition for Nighttime Image Dehazing","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.03339","title":"Hierarchical Awareness Adapters with Hybrid Pyramid Feature Fusion for Dense Depth Prediction","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.03553","title":"Chronos: The AI Co-Historian","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.19259","title":"Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.00885","title":"Multi-Branch Non-Homogeneous Image Dehazing via Concentration Partitioning and Image Fusion","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2605.18173","title":"Do You Need Text Rectification? Soft Attention Mask Embedding for Rectification-Free Scene Text Spotting","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2607.01602","title":"ProWAFT: A ROMA-LPD Instance for Workload-Aware and Dynamic Fault Tolerance in FPGA-Based CNN Accelerators","created":"2026-07-02","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":"2608.05848","title":"DTRNet: Dual Text-Radical Decoding for Handwritten Chinese Text Recognition with Faked Character Detection","created":"2026-08-06","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":"2608.14639","title":"Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Pays","created":"2026-07-28","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":"2608.24011","title":"SAGE: From Direct Answering to Evidence-Grounded Inference for Chinese Ancient Document Understanding","created":"2026-08-25","cited_by_count":0,"area":null},{"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":"2609.12475","title":"Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.13706","title":"Rank-Consistent Set Reasoning for Co-Salient Object Detection","created":"2026-09-12","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":"2609.29252","title":"IronViT: Toward Efficient Generalist Visual Representation Learning","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.31651","title":"PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions","created":"2026-09-14","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}],"next_cursor":null}