{"total":15,"rows":[{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740,"area":null},{"id":"2105.13626","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","created":"2021-05-28","cited_by_count":509,"area":null},{"id":"2207.02505","title":"Pure Transformers are Powerful Graph Learners","created":"2022-07-06","cited_by_count":188,"area":null},{"id":"2109.07740","title":"Scaling Laws for Neural Machine Translation","created":"2021-09-16","cited_by_count":111,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2204.02892","title":"Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks","created":"2022-04-06","cited_by_count":41,"area":null},{"id":"2110.04541","title":"The Inductive Bias of In-Context Learning: Rethinking Pretraining Example Design","created":"2021-10-09","cited_by_count":33,"area":null},{"id":"2201.11729","title":"Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks","created":"2022-01-27","cited_by_count":27,"area":null},{"id":"2111.01353","title":"Can Vision Transformers Perform Convolution?","created":"2021-11-02","cited_by_count":18,"area":null},{"id":"2211.16494","title":"On the Ability of Graph Neural Networks to Model Interactions Between Vertices","created":"2022-11-29","cited_by_count":12,"area":null},{"id":"2402.13301","title":"Structure-informed Positional Encoding for Music Generation","created":"2024-02-20","cited_by_count":5,"area":null},{"id":"2504.13558","title":"Transformers Can Overcome the Curse of Dimensionality: A Theoretical Study from an Approximation Perspective","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2510.07613","title":"Vocabulary embeddings organize linguistic structure early in language model training","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2208.04351","title":"Learning to Learn to Predict Performance Regressions in Production at Meta","created":"2022-08-08","cited_by_count":1,"area":null},{"id":"2208.08191","title":"Transformer Vs. MLP-Mixer: Exponential Expressive Gap For NLP Problems","created":"2022-08-17","cited_by_count":0,"area":null}],"next_cursor":null}