{"total":21,"rows":[{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2406.10252","title":"AutoSurvey: Large Language Models Can Automatically Write Surveys","created":"2024-06-10","cited_by_count":119,"area":null},{"id":"2202.08455","title":"Transformer for Graphs: An Overview from Architecture Perspective","created":"2022-02-17","cited_by_count":107,"area":null},{"id":"2102.11090","title":"Position Information in Transformers: An Overview","created":"2021-02-22","cited_by_count":103,"area":null},{"id":"2106.02795","title":"Learnable Fourier Features for Multi-Dimensional Spatial Positional Encoding","created":"2021-06-05","cited_by_count":93,"area":null},{"id":"2110.09681","title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","created":"2021-10-19","cited_by_count":68,"area":null},{"id":"2109.05244","title":"Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model","created":"2021-09-11","cited_by_count":18,"area":null},{"id":"2105.04037","title":"Graph Attention Networks with Positional Embeddings","created":"2021-05-09","cited_by_count":16,"area":null},{"id":"2206.04045","title":"STable: Table Generation Framework for Encoder-Decoder Models","created":"2022-06-08","cited_by_count":15,"area":null},{"id":"2109.10500","title":"HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning","created":"2021-09-22","cited_by_count":14,"area":null},{"id":"2101.06883","title":"CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering","created":"2021-01-18","cited_by_count":12,"area":null},{"id":"2106.02134","title":"Syntax-augmented Multilingual BERT for Cross-lingual Transfer","created":"2021-06-03","cited_by_count":11,"area":null},{"id":"2101.06980","title":"Mitigating the Position Bias of Transformer Models in Passage Re-Ranking","created":"2021-01-18","cited_by_count":10,"area":null},{"id":"2210.17027","title":"Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation","created":"2022-10-31","cited_by_count":9,"area":null},{"id":"2109.05388","title":"The Impact of Positional Encodings on Multilingual Compression","created":"2021-09-11","cited_by_count":5,"area":null},{"id":"2212.05830","title":"P-Transformer: Towards Better Document-to-Document Neural Machine Translation","created":"2022-12-12","cited_by_count":5,"area":null},{"id":"2310.16240","title":"Mixture-of-Linguistic-Experts Adapters for Improving and Interpreting Pre-trained Language Models","created":"2023-10-24","cited_by_count":2,"area":null},{"id":"2403.17525","title":"Equipping Sketch Patches with Context-Aware Positional Encoding for Graphic Sketch Representation","created":"2024-03-26","cited_by_count":2,"area":null},{"id":"2112.11913","title":"Trees in transformers: a theoretical analysis of the Transformer's ability to represent trees","created":"2021-12-16","cited_by_count":0,"area":null},{"id":"2404.09830","title":"Negation Triplet Extraction with Syntactic Dependency and Semantic Consistency","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2609.23551","title":"Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure","created":"2026-09-20","cited_by_count":0,"area":null}],"next_cursor":null}