{"list":"other","total":99,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"2203.10244","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","created":"2022-03-19","cited_by_count":1479},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2306.06070","title":"Mind2Web: Towards a Generalist Agent for the Web","created":"2023-06-09","cited_by_count":1242},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2401.10935","title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","created":"2024-01-17","cited_by_count":567},{"id":"1912.13318","title":"LayoutLM: Pre-training of Text and Layout for Document Image Understanding","created":"2019-12-31","cited_by_count":553},{"id":"1508.00305","title":"Compositional Semantic Parsing on Semi-Structured Tables","created":"2015-08-03","cited_by_count":515},{"id":"2104.12756","title":"InfographicVQA","created":"2021-04-26","cited_by_count":437},{"id":"1909.02164","title":"TabFact: A Large-scale Dataset for Table-based Fact Verification","created":"2019-09-05","cited_by_count":428},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2306.14289","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","created":"2023-06-25","cited_by_count":352},{"id":"1908.07836","title":"PubLayNet: largest dataset ever for document layout analysis","created":"2019-08-16","cited_by_count":351},{"id":"2209.14610","title":"Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning","created":"2022-09-29","cited_by_count":350},{"id":"1801.08163","title":"DVQA: Understanding Data Visualizations via Question Answering","created":"2018-01-24","cited_by_count":340},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"1710.07300","title":"FigureQA: An Annotated Figure Dataset for Visual Reasoning","created":"2017-10-19","cited_by_count":319},{"id":"2311.07575","title":"SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models","created":"2023-11-13","cited_by_count":286},{"id":"2306.17107","title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","created":"2023-06-29","cited_by_count":274},{"id":"2305.18565","title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","created":"2023-05-29","cited_by_count":255},{"id":"2311.07113","title":"SpectralGPT: Spectral Remote Sensing Foundation Model","created":"2023-11-13","cited_by_count":252},{"id":"2411.10442","title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","created":"2024-11-15","cited_by_count":239},{"id":"1911.10683","title":"Image-based table recognition: data, model, and evaluation","created":"2019-11-25","cited_by_count":237},{"id":"1601.07140","title":"COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images","created":"2016-01-26","cited_by_count":236},{"id":"2403.09611","title":"MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training","created":"2024-03-14","cited_by_count":232},{"id":"2403.12895","title":"mPLUG-DocOwl 1.5: Unified Structure Learning for OCR-free Document Understanding","created":"2024-03-19","cited_by_count":220},{"id":"1502.07058","title":"Evaluation of Deep Convolutional Nets for Document Image Classification and Retrieval","created":"2015-02-25","cited_by_count":213},{"id":"2410.07073","title":"Pixtral 12B","created":"2024-10-09","cited_by_count":179},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173},{"id":"2407.02392","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","created":"2024-07-02","cited_by_count":172},{"id":"2105.05486","title":"TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text","created":"2021-05-12","cited_by_count":171},{"id":"2002.10200","title":"ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network","created":"2020-02-24","cited_by_count":170},{"id":"2405.20797","title":"Ovis: Structural Embedding Alignment for Multimodal Large Language Model","created":"2024-05-31","cited_by_count":169},{"id":"1710.10400","title":"Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition","created":"2017-10-28","cited_by_count":162},{"id":"2402.17553","title":"OmniACT: A Dataset and Benchmark for Enabling Multimodal Generalist Autonomous Agents for Desktop and Web","created":"2024-02-27","cited_by_count":157},{"id":"2101.11272","title":"VisualMRC: Machine Reading Comprehension on Document Images","created":"2021-01-27","cited_by_count":151},{"id":"1909.07145","title":"ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)","created":"2019-09-16","cited_by_count":147},{"id":"2310.05126","title":"UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model","created":"2023-10-08","cited_by_count":143},{"id":"2408.15998","title":"Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders","created":"2024-08-28","cited_by_count":139},{"id":"2403.09029","title":"Unlocking the conversion of Web Screenshots into HTML Code with the WebSight Dataset","created":"2024-03-14","cited_by_count":129},{"id":"1912.09641","title":"ICDAR 2019 Robust Reading Challenge on Reading Chinese Text on Signboard","created":"2019-12-20","cited_by_count":128},{"id":"1909.07741","title":"ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT","created":"2019-09-17","cited_by_count":122},{"id":"2108.03353","title":"Screen2Words: Automatic Mobile UI Summarization with Multimodal Learning","created":"2021-08-07","cited_by_count":120},{"id":"2401.00908","title":"DocLLM: A layout-aware generative language model for multimodal document understanding","created":"2023-12-31","cited_by_count":116},{"id":"2202.06767","title":"Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark","created":"2022-02-14","cited_by_count":114},{"id":"2409.03420","title":"mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document Understanding","created":"2024-09-05","cited_by_count":114},{"id":"1709.02054","title":"Focusing Attention: Towards Accurate Text Recognition in Natural Images","created":"2017-09-07","cited_by_count":110},{"id":"1708.09585","title":"ICDAR2017 Competition on Reading Chinese Text in the Wild (RCTW-17)","created":"2017-08-31","cited_by_count":105},{"id":"2203.15143","title":"Towards End-to-End Unified Scene Text Detection and Layout Analysis","created":"2022-03-28","cited_by_count":97},{"id":"2309.11419","title":"KOSMOS-2.5: A Multimodal Literate Model","created":"2023-09-20","cited_by_count":96},{"id":"1712.02170","title":"Detecting Curve Text in the Wild: New Dataset and New Solution","created":"2017-12-06","cited_by_count":83},{"id":"2105.05796","title":"Kleister: Key Information Extraction Datasets Involving Long Documents with Complex Layouts","created":"2021-05-12","cited_by_count":82},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76},{"id":"2308.11592","title":"UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding","created":"2023-08-19","cited_by_count":74},{"id":"2407.01976","title":"A Bounding Box is Worth One Token: Interleaving Layout and Text in a Large Language Model for Document Understanding","created":"2024-07-02","cited_by_count":57},{"id":"2106.12326","title":"Open Images V5 Text Annotation and Yet Another Mask Text Spotter","created":"2021-06-23","cited_by_count":46},{"id":"2207.01223","title":"A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction","created":"2022-07-04","cited_by_count":46},{"id":"2302.14338","title":"Turning a CLIP Model into a Scene Text Detector","created":"2023-02-28","cited_by_count":44},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36},{"id":"2410.05261","title":"TextHawk2: A Large Vision-Language Model Excels in Bilingual OCR and Grounding with 16x Fewer Tokens","created":"2024-10-07","cited_by_count":32},{"id":"2401.17904","title":"Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation","created":"2024-01-31","cited_by_count":30},{"id":"2211.00288","title":"Self-supervised Character-to-Character Distillation for Text Recognition","created":"2022-11-01","cited_by_count":27},{"id":"2401.13313","title":"InstructDoc: A Dataset for Zero-Shot Generalization of Visual Document Understanding with Instructions","created":"2024-01-24","cited_by_count":27},{"id":"2404.09204","title":"TextHawk: Exploring Efficient Fine-Grained Perception of Multimodal Large Language Models","created":"2024-04-14","cited_by_count":27},{"id":"2408.02034","title":"Mini-Monkey: Alleviating the Semantic Sawtooth Effect for Lightweight MLLMs via Complementary Image Pyramid","created":"2024-08-04","cited_by_count":26},{"id":"2203.03382","title":"Self-supervised Implicit Glyph Attention for Text Recognition","created":"2022-03-07","cited_by_count":25},{"id":"2401.17221","title":"MouSi: Poly-Visual-Expert Vision-Language Models","created":"2024-01-30","cited_by_count":24},{"id":"2407.14439","title":"Token-level Correlation-guided Compression for Efficient Multimodal Document Understanding","created":"2024-07-19","cited_by_count":22},{"id":"2304.14953","title":"CCpdf: Building a High Quality Corpus for Visually Rich Documents from Web Crawl Data","created":"2023-04-28","cited_by_count":21},{"id":"2407.07764","title":"PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer","created":"2024-07-10","cited_by_count":18},{"id":"2110.12663","title":"Industrial Scene Text Detection with Refined Feature-attentive Network","created":"2021-10-25","cited_by_count":16},{"id":"2104.01552","title":"Scene Text Retrieval via Joint Text Detection and Similarity Learning","created":"2021-04-04","cited_by_count":15},{"id":"2407.14506","title":"On Pre-training of Multimodal Language Models Customized for Chart Understanding","created":"2024-07-19","cited_by_count":13},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13},{"id":"2006.06434","title":"TableQA: a Large-Scale Chinese Text-to-SQL Dataset for Table-Aware SQL Generation","created":"2020-06-10","cited_by_count":12},{"id":"2312.05286","title":"Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors","created":"2023-12-08","cited_by_count":9},{"id":"2502.16586","title":"Multimodal Large Language Models for Text-rich Image Understanding: A Comprehensive Review","created":"2025-02-23","cited_by_count":9}],"next_cursor":null}