{"list":"other","total":53,"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"1710.10903","title":"Graph Attention Networks","created":"2017-10-30","cited_by_count":8923},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2307.03172","title":"Lost in the Middle: How Language Models Use Long Contexts","created":"2023-07-06","cited_by_count":3455},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1606.09375","title":"Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering","created":"2016-06-30","cited_by_count":2089},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1902.07153","title":"Simplifying Graph Convolutional Networks","created":"2019-02-19","cited_by_count":1477},{"id":"1810.05997","title":"Predict then Propagate: Graph Neural Networks meet Personalized PageRank","created":"2018-10-14","cited_by_count":993},{"id":"1603.08861","title":"Revisiting Semi-Supervised Learning with Graph Embeddings","created":"2016-03-29","cited_by_count":976},{"id":"1806.03536","title":"Representation Learning on Graphs with Jumping Knowledge Networks","created":"2018-06-09","cited_by_count":877},{"id":"2007.02133","title":"Simple and Deep Graph Convolutional Networks","created":"2020-07-04","cited_by_count":860},{"id":"1802.05751","title":"Image Transformer","created":"2018-02-15","cited_by_count":772},{"id":"2302.00083","title":"In-Context Retrieval-Augmented Language Models","created":"2023-01-31","cited_by_count":702},{"id":"2006.05205","title":"On the Bottleneck of Graph Neural Networks and its Practical Implications","created":"2020-06-09","cited_by_count":631},{"id":"1801.10247","title":"FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling","created":"2018-01-30","cited_by_count":584},{"id":"1905.07953","title":"Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks","created":"2019-05-20","cited_by_count":541},{"id":"1911.06455","title":"Graph Transformer Networks","created":"2019-11-06","cited_by_count":523},{"id":"2307.03393","title":"Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs","created":"2023-07-07","cited_by_count":274},{"id":"2310.00149","title":"One for All: Towards Training One Graph Model for All Classification Tasks","created":"2023-09-29","cited_by_count":243},{"id":"2308.07134","title":"Language is All a Graph Needs","created":"2023-08-14","cited_by_count":220},{"id":"2305.15066","title":"GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking","created":"2023-05-24","cited_by_count":210},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2402.08170","title":"LLaGA: Large Language and Graph Assistant","created":"2024-02-13","cited_by_count":181},{"id":"1902.01718","title":"End-to-End Open-Domain Question Answering with BERTserini","created":"2019-02-05","cited_by_count":152},{"id":"1808.03965","title":"Large-Scale Learnable Graph Convolutional Networks","created":"2018-08-12","cited_by_count":113},{"id":"2011.09315","title":"End-to-End Object Detection with Adaptive Clustering Transformer","created":"2020-11-18","cited_by_count":109},{"id":"1803.03735","title":"Attention-based Graph Neural Network for Semi-supervised Learning","created":"2018-03-10","cited_by_count":101},{"id":"2310.04668","title":"Label-free Node Classification on Graphs with Large Language Models (LLMS)","created":"2023-10-07","cited_by_count":72},{"id":"1905.05460","title":"Cognitive Graph for Multi-Hop Reading Comprehension at Scale","created":"2019-05-14","cited_by_count":65},{"id":"2210.07494","title":"A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinking","created":"2022-10-14","cited_by_count":56},{"id":"2101.06323","title":"TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search","created":"2021-01-15","cited_by_count":54},{"id":"2003.13606","title":"L$^2$-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks","created":"2020-03-30","cited_by_count":48},{"id":"2207.10040","title":"Single Frame Atmospheric Turbulence Mitigation: A Benchmark Study and A New Physics-Inspired Transformer Model","created":"2022-07-20","cited_by_count":37},{"id":"2108.10521","title":"Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study","created":"2021-08-24","cited_by_count":36},{"id":"2305.00909","title":"Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation","created":"2023-04-28","cited_by_count":27},{"id":"2310.09872","title":"Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs","created":"2023-10-15","cited_by_count":23},{"id":"2110.15426","title":"RadBERT-CL: Factually-Aware Contrastive Learning For Radiology Report Classification","created":"2021-10-28","cited_by_count":13},{"id":"2210.08122","title":"Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again","created":"2022-10-14","cited_by_count":11},{"id":"2105.14428","title":"DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation","created":"2021-05-30","cited_by_count":3}],"next_cursor":null}