{"list":"other","total":78,"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":"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"2005.00687","title":"Open Graph Benchmark: Datasets for Machine Learning on Graphs","created":"2020-05-02","cited_by_count":2163},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1306.5151","title":"Fine-Grained Visual Classification of Aircraft","created":"2013-06-21","cited_by_count":1726},{"id":"1709.00029","title":"EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification","created":"2017-08-31","cited_by_count":1496},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2103.07191","title":"Are NLP Models really able to Solve Simple Math Word Problems?","created":"2021-03-12","cited_by_count":878},{"id":"1703.00121","title":"Remote Sensing Image Scene Classification: Benchmark and State of the Art","created":"2017-03-01","cited_by_count":797},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"1705.08039","title":"Poincar\\'e Embeddings for Learning Hierarchical Representations","created":"2017-05-22","cited_by_count":684},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"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":"1804.09301","title":"Gender Bias in Coreference Resolution","created":"2018-04-25","cited_by_count":442},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"1805.09112","title":"Hyperbolic Neural Networks","created":"2018-05-23","cited_by_count":402},{"id":"1910.12933","title":"Hyperbolic Graph Convolutional Neural Networks","created":"2019-10-28","cited_by_count":402},{"id":"1806.03417","title":"Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry","created":"2018-06-09","cited_by_count":265},{"id":"1910.12892","title":"Hyperbolic Graph Neural Networks","created":"2019-10-28","cited_by_count":244},{"id":"2311.10723","title":"Large Language Models in Finance: A Survey","created":"2023-09-28","cited_by_count":226},{"id":"2005.00545","title":"Low-Dimensional Hyperbolic Knowledge Graph Embeddings","created":"2020-05-01","cited_by_count":195},{"id":"1810.00760","title":"Riemannian Adaptive Optimization Methods","created":"2018-10-01","cited_by_count":194},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"1910.09753","title":"MRQA 2019 Shared Task: Evaluating Generalization in Reading Comprehension","created":"2019-10-22","cited_by_count":184},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180},{"id":"1804.01882","title":"Hyperbolic Entailment Cones for Learning Hierarchical Embeddings","created":"2018-04-03","cited_by_count":162},{"id":"1810.06546","title":"Poincar\\'e GloVe: Hyperbolic Word Embeddings","created":"2018-10-15","cited_by_count":156},{"id":"2105.07464","title":"Few-NERD: A Few-Shot Named Entity Recognition Dataset","created":"2021-05-16","cited_by_count":152},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139},{"id":"2105.14686","title":"Fully Hyperbolic Neural Networks","created":"2021-05-31","cited_by_count":108},{"id":"2004.14855","title":"TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task","created":"2020-04-30","cited_by_count":96},{"id":"1807.04905","title":"Ultra-Fine Entity Typing","created":"2018-07-13","cited_by_count":87},{"id":"2104.08398","title":"Re-TACRED: Addressing Shortcomings of the TACRED Dataset","created":"2021-04-16","cited_by_count":74},{"id":"1605.07147","title":"Riemannian SVRG: Fast Stochastic Optimization on Riemannian Manifolds","created":"2016-05-23","cited_by_count":64},{"id":"1705.10359","title":"Neural Embeddings of Graphs in Hyperbolic Space","created":"2017-05-29","cited_by_count":58},{"id":"2211.00181","title":"The Numerical Stability of Hyperbolic Representation Learning","created":"2022-10-31","cited_by_count":47},{"id":"2401.09646","title":"ClimateGPT: Towards AI Synthesizing Interdisciplinary Research on Climate Change","created":"2024-01-17","cited_by_count":47},{"id":"2004.03459","title":"Hierarchical Image Classification using Entailment Cone Embeddings","created":"2020-04-02","cited_by_count":46},{"id":"2407.01290","title":"Hypformer: Exploring Efficient Transformer Fully in Hyperbolic Space","created":"2024-07-01","cited_by_count":43},{"id":"2202.13852","title":"Hyperbolic Graph Neural Networks: A Review of Methods and Applications","created":"2022-02-28","cited_by_count":40},{"id":"2304.14721","title":"Towards autonomous system: flexible modular production system enhanced with large language model agents","created":"2023-04-28","cited_by_count":39},{"id":"2404.00532","title":"LLMs are Good Action Recognizers","created":"2024-03-31","cited_by_count":37},{"id":"2001.03241","title":"Network Geometry","created":"2020-01-09","cited_by_count":31},{"id":"2401.11374","title":"Language Models as Hierarchy Encoders","created":"2024-01-21","cited_by_count":28},{"id":"2410.04010","title":"Hyperbolic Fine-Tuning for Large Language Models","created":"2024-10-05","cited_by_count":27},{"id":"2505.24722","title":"HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts","created":"2025-05-30","cited_by_count":26},{"id":"1908.04895","title":"HyperKG: Hyperbolic Knowledge Graph Embeddings for Knowledge Base Completion","created":"2019-08-14","cited_by_count":20},{"id":"2412.14695","title":"Lorentzian Residual Neural Networks","created":"2024-12-19","cited_by_count":17},{"id":"2108.04607","title":"Fully Hyperbolic Graph Convolution Network for Recommendation","created":"2021-08-10","cited_by_count":13},{"id":"2504.08912","title":"HyperCore: The Core Framework for Building Hyperbolic Foundation Models with Comprehensive Modules","created":"2025-04-11","cited_by_count":12},{"id":"2406.16508","title":"Large Vocabulary Size Improves Large Language Models","created":"2024-06-24","cited_by_count":11},{"id":"2505.09205","title":"HMamba: Hyperbolic Mamba for Sequential Recommendation","created":"2025-05-14","cited_by_count":11},{"id":"2408.05097","title":"Hyperbolic Learning with Multimodal Large Language Models","created":"2024-08-09","cited_by_count":10},{"id":"2407.05437","title":"Enhancing Computer Programming Education with LLMs: A Study on Effective Prompt Engineering for Python Code Generation","created":"2024-07-07","cited_by_count":9},{"id":"2406.09833","title":"SHMamba: Structured Hyperbolic State Space Model for Audio-Visual Question Answering","created":"2024-06-14","cited_by_count":7},{"id":"2505.18973","title":"Hierarchical Mamba Meets Hyperbolic Geometry: A New Paradigm for Structured Language Embeddings","created":"2025-05-25","cited_by_count":6},{"id":"2211.03635","title":"Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform","created":"2022-11-07","cited_by_count":5},{"id":"2405.15481","title":"Sparse Spectral Training and Inference on Euclidean and Hyperbolic Neural Networks","created":"2024-05-24","cited_by_count":4},{"id":"2502.05869","title":"HyLiFormer: Hyperbolic Linear Attention for Skeleton-based Human Action Recognition","created":"2025-02-09","cited_by_count":4},{"id":"2412.11293","title":"A Comparative Study on Dynamic Graph Embedding based on Mamba and Transformers","created":"2024-12-15","cited_by_count":3},{"id":"2406.15472","title":"Hyperbolic sentence representations for solving Textual Entailment","created":"2024-06-15","cited_by_count":2},{"id":"2503.13862","title":"HySurvPred: Multimodal Hyperbolic Embedding with Angle-Aware Hierarchical Contrastive Learning and Uncertainty Constraints for Survival Prediction","created":"2025-03-18","cited_by_count":2},{"id":"2504.05694","title":"Large Language Models Enhanced Hyperbolic Space Recommender Systems","created":"2025-04-08","cited_by_count":2},{"id":"2508.07106","title":"BrainATCL: Adaptive Temporal Brain Connectivity Learning for Functional Link Prediction and Age Estimation","created":"2025-08-09","cited_by_count":1}],"next_cursor":null}