{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2306.04637","title":"Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection","created":"2023-06-07","cited_by_count":298},{"id":"1906.06755","title":"Theoretical Limitations of Self-Attention in Neural Sequence Models","created":"2019-06-16","cited_by_count":288},{"id":"2212.09196","title":"Emergent Analogical Reasoning in Large Language Models","created":"2022-12-19","cited_by_count":240},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"2207.00112","title":"Language model compression with weighted low-rank factorization","created":"2022-06-30","cited_by_count":195},{"id":"2106.06981","title":"Thinking Like Transformers","created":"2021-06-13","cited_by_count":184},{"id":"2312.10794","title":"A mathematical perspective on Transformers","created":"2023-12-17","cited_by_count":164},{"id":"2306.00802","title":"Birth of a Transformer: A Memory Viewpoint","created":"2023-06-01","cited_by_count":161},{"id":"2306.17844","title":"The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks","created":"2023-06-30","cited_by_count":156},{"id":"2203.16634","title":"Transformer Language Models without Positional Encodings Still Learn Positional Information","created":"2022-03-30","cited_by_count":150},{"id":"2306.15063","title":"Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression","created":"2023-06-26","cited_by_count":146},{"id":"2110.10090","title":"Inductive Biases and Variable Creation in Self-Attention Mechanisms","created":"2021-10-19","cited_by_count":144},{"id":"1511.02476","title":"Statistical physics of inference: Thresholds and algorithms","created":"2015-11-08","cited_by_count":128},{"id":"2309.07311","title":"Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs","created":"2023-09-13","cited_by_count":124},{"id":"2312.03002","title":"The mechanistic basis of data dependence and abrupt learning in an in-context classification task","created":"2023-12-03","cited_by_count":118},{"id":"2305.16843","title":"Randomized Positional Encodings Boost Length Generalization of Transformers","created":"2023-05-26","cited_by_count":117},{"id":"1708.03395","title":"Optimal Errors and Phase Transitions in High-Dimensional Generalized Linear Models","created":"2017-08-10","cited_by_count":116},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113},{"id":"2305.16380","title":"Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer","created":"2023-05-25","cited_by_count":102},{"id":"2210.09221","title":"Vision Transformers provably learn spatial structure","created":"2022-10-13","cited_by_count":93},{"id":"2302.06015","title":"A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity","created":"2023-02-12","cited_by_count":77},{"id":"2311.08360","title":"The Transient Nature of Emergent In-Context Learning in Transformers","created":"2023-11-14","cited_by_count":76},{"id":"2310.10616","title":"How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations","created":"2023-10-16","cited_by_count":75},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74},{"id":"2002.11544","title":"The role of regularization in classification of high-dimensional noisy Gaussian mixture","created":"2020-02-26","cited_by_count":63},{"id":"1806.05451","title":"The committee machine: Computational to statistical gaps in learning a two-layers neural network","created":"2018-06-14","cited_by_count":58},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2106.03791","title":"Learning Gaussian Mixtures with Generalised Linear Models: Precise Asymptotics in High-dimensions","created":"2021-06-07","cited_by_count":54},{"id":"2306.07042","title":"Transformers learn through gradual rank increase","created":"2023-06-12","cited_by_count":52},{"id":"2006.06560","title":"Generalization error in high-dimensional perceptrons: Approaching Bayes error with convex optimization","created":"2020-06-11","cited_by_count":51},{"id":"2307.11353","title":"What can a Single Attention Layer Learn? A Study Through the Random Features Lens","created":"2023-07-21","cited_by_count":40},{"id":"2006.05228","title":"Phase retrieval in high dimensions: Statistical and computational phase transitions","created":"2020-06-09","cited_by_count":39},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30},{"id":"2005.00180","title":"Generalization Error of Generalized Linear Models in High Dimensions","created":"2020-05-01","cited_by_count":25},{"id":"2006.06581","title":"Asymptotic Errors for Teacher-Student Convex Generalized Linear Models (or : How to Prove Kabashima's Replica Formula)","created":"2020-06-11","cited_by_count":23},{"id":"1612.03132","title":"Phase transitions in Restricted Boltzmann Machines with generic priors","created":"2016-12-09","cited_by_count":20},{"id":"1906.06766","title":"Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias","created":"2019-06-16","cited_by_count":19},{"id":"2305.11041","title":"High-dimensional Asymptotics of Denoising Autoencoders","created":"2023-05-18","cited_by_count":19},{"id":"2202.03295","title":"Theoretical characterization of uncertainty in high-dimensional linear classification","created":"2022-02-07","cited_by_count":18},{"id":"2203.12094","title":"Learning curves for the multi-class teacher-student perceptron","created":"2022-03-22","cited_by_count":17},{"id":"2210.12574","title":"The Curious Case of Absolute Position Embeddings","created":"2022-10-23","cited_by_count":17},{"id":"1303.7289","title":"Upper-bounding $\\ell_1$-optimization weak thresholds","created":"2013-03-29","cited_by_count":14},{"id":"1304.0003","title":"Meshes that trap random subspaces","created":"2013-03-29","cited_by_count":8}],"next_cursor":null}