{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"1804.08771","title":"A Call for Clarity in Reporting BLEU Scores","created":"2018-04-23","cited_by_count":1799},{"id":"2211.12588","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","created":"2022-11-22","cited_by_count":1076},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"1603.06937","title":"Stacked Hourglass Networks for Human Pose Estimation","created":"2016-03-22","cited_by_count":915},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366},{"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":"2402.14289","title":"TinyLLaVA: A Framework of Small-scale Large Multimodal Models","created":"2024-02-22","cited_by_count":164},{"id":"2311.16483","title":"ChartLlama: A Multimodal LLM for Chart Understanding and Generation","created":"2023-11-27","cited_by_count":163},{"id":"2311.10774","title":"MMC: Advancing Multimodal Chart Understanding with Large-scale Instruction Tuning","created":"2023-11-15","cited_by_count":150},{"id":"2402.12185","title":"ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning","created":"2024-02-19","cited_by_count":128},{"id":"2312.15915","title":"ChartBench: A Benchmark for Complex Visual Reasoning in Charts","created":"2023-12-26","cited_by_count":120},{"id":"2401.02384","title":"ChartAssisstant: A Universal Chart Multimodal Language Model via Chart-to-Table Pre-training and Multitask Instruction Tuning","created":"2024-01-04","cited_by_count":79},{"id":"2010.09142","title":"Chart-to-Text: Generating Natural Language Descriptions for Charts by Adapting the Transformer Model","created":"2020-10-18","cited_by_count":78},{"id":"2403.09028","title":"ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning","created":"2024-03-14","cited_by_count":68},{"id":"2012.08561","title":"Pre-Training Transformers as Energy-Based Cloze Models","created":"2020-12-15","cited_by_count":52},{"id":"2404.16635","title":"TinyChart: Efficient Chart Understanding with Visual Token Merging and Program-of-Thoughts Learning","created":"2024-04-25","cited_by_count":52},{"id":"2312.10160","title":"Do LVLMs Understand Charts? Analyzing and Correcting Factual Errors in Chart Captioning","created":"2023-12-15","cited_by_count":49},{"id":"2310.08184","title":"Learning from models beyond fine-tuning","created":"2023-10-12","cited_by_count":48},{"id":"2401.12503","title":"Small Language Model Meets with Reinforced Vision Vocabulary","created":"2024-01-23","cited_by_count":43},{"id":"2404.09987","title":"OneChart: Purify the Chart Structural Extraction via One Auxiliary Token","created":"2024-04-15","cited_by_count":39},{"id":"2301.11843","title":"Reading and Reasoning over Chart Images for Evidence-based Automated Fact-Checking","created":"2023-01-27","cited_by_count":35},{"id":"2104.12714","title":"Focused Attention Improves Document-Grounded Generation","created":"2021-04-26","cited_by_count":24},{"id":"1711.05962","title":"Beagle: Automated Extraction and Interpretation of Visualizations from the Web","created":"2017-11-16","cited_by_count":19},{"id":"2309.11268","title":"StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding","created":"2023-09-20","cited_by_count":19},{"id":"2305.18641","title":"Enhanced Chart Understanding in Vision and Language Task via Cross-modal Pre-training on Plot Table Pairs","created":"2023-05-29","cited_by_count":15},{"id":"2401.14010","title":"Leveraging Foundation Models for Crafting Narrative Visualization: A Survey","created":"2024-01-25","cited_by_count":9},{"id":"2404.01548","title":"mChartQA: A universal benchmark for multimodal Chart Question Answer based on Vision-Language Alignment and Reasoning","created":"2024-04-02","cited_by_count":9},{"id":"2405.00021","title":"SIMPLOT: Enhancing Chart Question Answering by Distilling Essentials","created":"2024-02-22","cited_by_count":7},{"id":"2307.03254","title":"Vision Language Transformers: A Survey","created":"2023-07-06","cited_by_count":5},{"id":"2405.19094","title":"Faithful Chart Summarization with ChaTS-Pi","created":"2024-05-29","cited_by_count":5},{"id":"1912.10435","title":"BERTQA -- Attention on Steroids","created":"2019-12-14","cited_by_count":3},{"id":"2405.00748","title":"ChatGPT in Data Visualization Education: A Student Perspective","created":"2024-05-01","cited_by_count":3},{"id":"2402.14579","title":"Text Role Classification in Scientific Charts Using Multimodal Transformers","created":"2024-02-08","cited_by_count":1}],"next_cursor":null}