{"list":"other","total":51,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2303.16634","title":"G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment","created":"2023-03-29","cited_by_count":2276},{"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":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2111.15664","title":"OCR-free Document Understanding Transformer","created":"2021-11-30","cited_by_count":407},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"id":"1909.00997","title":"PlotQA: Reasoning over Scientific Plots","created":"2019-09-03","cited_by_count":321},{"id":"2303.09540","title":"SemDeDup: Data-efficient learning at web-scale through semantic deduplication","created":"2023-03-16","cited_by_count":303},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2312.06742","title":"Honeybee: Locality-enhanced Projector for Multimodal LLM","created":"2023-12-11","cited_by_count":197},{"id":"2203.06486","title":"Chart-to-Text: A Large-Scale Benchmark for Chart Summarization","created":"2022-03-12","cited_by_count":169},{"id":"2212.10505","title":"DePlot: One-shot visual language reasoning by plot-to-table translation","created":"2022-12-20","cited_by_count":160},{"id":"2402.11530","title":"Efficient Multimodal Learning from Data-centric Perspective","created":"2024-02-18","cited_by_count":122},{"id":"2403.03003","title":"Feast Your Eyes: Mixture-of-Resolution Adaptation for Multimodal Large Language Models","created":"2024-03-05","cited_by_count":113},{"id":"2307.05356","title":"VisText: A Benchmark for Semantically Rich Chart Captioning","created":"2023-06-28","cited_by_count":112},{"id":"2403.09028","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","created":"2024-03-14","cited_by_count":68},{"id":"1808.04819","title":"VizML: A Machine Learning Approach to Visualization Recommendation","created":"2018-08-14","cited_by_count":38},{"id":"2304.13620","title":"ChartSumm: A Comprehensive Benchmark for Automatic Chart Summarization of Long and Short Summaries","created":"2023-04-26","cited_by_count":32},{"id":"2311.01487","title":"What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning","created":"2023-11-02","cited_by_count":28},{"id":"2205.03966","title":"Chart Question Answering: State of the Art and Future Directions","created":"2022-05-08","cited_by_count":26},{"id":"2310.07652","title":"LLM4Vis: Explainable Visualization Recommendation using ChatGPT","created":"2023-10-11","cited_by_count":25},{"id":"2304.02173","title":"ChartReader: A Unified Framework for Chart Derendering and Comprehension without Heuristic Rules","created":"2023-04-05","cited_by_count":24},{"id":"2304.14630","title":"Let the Chart Spark: Embedding Semantic Context into Chart with Text-to-Image Generative Model","created":"2023-04-28","cited_by_count":21},{"id":"2309.10245","title":"Natural Language Dataset Generation Framework for Visualizations Powered by Large Language Models","created":"2023-09-19","cited_by_count":20},{"id":"1711.05962","title":"Beagle: Automated Extraction and Interpretation of Visualizations from the Web","created":"2017-11-16","cited_by_count":19},{"id":"2107.12548","title":"KG4Vis: A Knowledge Graph-Based Approach for Visualization Recommendation","created":"2021-07-27","cited_by_count":17},{"id":"2304.07905","title":"Mini-VLAT: A Short and Effective Measure of Visualization Literacy","created":"2023-04-16","cited_by_count":16},{"id":"2101.01036","title":"VIS30K: A Collection of Figures and Tables from IEEE Visualization Conference Publications","created":"2020-12-22","cited_by_count":13},{"id":"2208.01232","title":"DashBot: Insight-Driven Dashboard Generation Based on Deep Reinforcement Learning","created":"2022-08-02","cited_by_count":10},{"id":"2312.10610","title":"Do LLMs Work on Charts? Designing Few-Shot Prompts for Chart Question Answering and Summarization","created":"2023-12-17","cited_by_count":10},{"id":"2007.15407","title":"Composition and Configuration Patterns in Multiple-View Visualizations","created":"2020-07-30","cited_by_count":7},{"id":"2007.04584","title":"VisImages: A Fine-Grained Expert-Annotated Visualization Dataset","created":"2020-07-09","cited_by_count":6},{"id":"2304.06991","title":"WYTIWYR: A User Intent-Aware Framework with Multi-modal Inputs for Visualization Retrieval","created":"2023-04-14","cited_by_count":6},{"id":"2203.10476","title":"Revisiting the Design Patterns of Composite Visualizations","created":"2022-03-20","cited_by_count":1}],"next_cursor":null}