{"list":"other","total":57,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1405.4980","title":"Convex Optimization: Algorithms and Complexity","created":"2014-05-20","cited_by_count":575},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"1906.05890","title":"Gradient Descent Maximizes the Margin of Homogeneous Neural Networks","created":"2019-06-13","cited_by_count":320},{"id":"2002.04486","title":"Implicit Bias of Gradient Descent for Wide Two-layer Neural Networks Trained with the Logistic Loss","created":"2020-02-11","cited_by_count":268},{"id":"1802.08246","title":"Characterizing Implicit Bias in Terms of Optimization Geometry","created":"2018-02-22","cited_by_count":266},{"id":"2006.06657","title":"Directional convergence and alignment in deep learning","created":"2020-06-11","cited_by_count":178},{"id":"2012.09839","title":"Towards Resolving the Implicit Bias of Gradient Descent for Matrix Factorization: Greedy Low-Rank Learning","created":"2020-12-17","cited_by_count":150},{"id":"2310.05249","title":"In-Context Convergence of Transformers","created":"2023-10-08","cited_by_count":115},{"id":"1803.01905","title":"Convergence of Gradient Descent on Separable Data","created":"2018-03-05","cited_by_count":110},{"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":"2208.12591","title":"On the Implicit Bias in Deep-Learning Algorithms","created":"2022-08-26","cited_by_count":86},{"id":"1803.07300","title":"Risk and parameter convergence of logistic regression","created":"2018-03-20","cited_by_count":85},{"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":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74},{"id":"2402.19442","title":"Training Dynamics of Multi-Head Softmax Attention for In-Context Learning: Emergence, Convergence, and Optimality","created":"2024-02-29","cited_by_count":74},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58},{"id":"2310.00535","title":"JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention","created":"2023-10-01","cited_by_count":52},{"id":"2306.03435","title":"On the Role of Attention in Prompt-tuning","created":"2023-06-06","cited_by_count":50},{"id":"2310.17086","title":"Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression","created":"2023-10-26","cited_by_count":49},{"id":"2210.07082","title":"Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data","created":"2022-10-13","cited_by_count":46},{"id":"2012.05156","title":"Implicit Regularization in ReLU Networks with the Square Loss","created":"2020-12-09","cited_by_count":45},{"id":"1906.03830","title":"Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization","created":"2019-06-10","cited_by_count":40},{"id":"2401.15530","title":"An Information-Theoretic Analysis of In-Context Learning","created":"2024-01-28","cited_by_count":40},{"id":"2402.04161","title":"Attention with Markov: A Framework for Principled Analysis of Transformers via Markov Chains","created":"2024-02-06","cited_by_count":40},{"id":"2310.12680","title":"On the Optimization and Generalization of Multi-head Attention","created":"2023-10-19","cited_by_count":37},{"id":"2402.13512","title":"From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers","created":"2024-02-21","cited_by_count":34},{"id":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34},{"id":"2107.00595","title":"Fast Margin Maximization via Dual Acceleration","created":"2021-07-01","cited_by_count":33},{"id":"2402.05738","title":"Implicit Bias and Fast Convergence Rates for Self-attention","created":"2024-02-08","cited_by_count":31},{"id":"2205.08078","title":"Unraveling Attention via Convex Duality: Analysis and Interpretations of Vision Transformers","created":"2022-05-17","cited_by_count":30},{"id":"1806.00952","title":"Stochastic Gradient/Mirror Descent: Minimax Optimality and Implicit Regularization","created":"2018-06-04","cited_by_count":29},{"id":"2205.12808","title":"Mirror Descent Maximizes Generalized Margin and Can Be Implemented Efficiently","created":"2022-05-25","cited_by_count":26},{"id":"2408.15417","title":"Implicit Geometry of Next-token Prediction: From Language Sparsity Patterns to Model Representations","created":"2024-08-27","cited_by_count":24},{"id":"2402.11639","title":"In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness","created":"2024-02-18","cited_by_count":22},{"id":"2406.06893","title":"Transformers Provably Learn Sparse Token Selection While Fully-Connected Nets Cannot","created":"2024-06-11","cited_by_count":22},{"id":"2402.04084","title":"Provably learning a multi-head attention layer","created":"2024-02-06","cited_by_count":21},{"id":"2402.02098","title":"Self-attention Networks Localize When QK-eigenspectrum Concentrates","created":"2024-02-03","cited_by_count":19},{"id":"2403.08699","title":"Implicit Regularization of Gradient Flow on One-Layer Softmax Attention","created":"2024-03-13","cited_by_count":19},{"id":"2306.13853","title":"A Unified Approach to Controlling Implicit Regularization via Mirror Descent","created":"2023-06-24","cited_by_count":14},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14},{"id":"2403.06925","title":"Transformers Learn Low Sensitivity Functions: Investigations and Implications","created":"2024-03-11","cited_by_count":14},{"id":"2312.07887","title":"Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models","created":"2023-12-13","cited_by_count":13},{"id":"2409.17335","title":"Non-asymptotic Convergence of Training Transformers for Next-token Prediction","created":"2024-09-25","cited_by_count":13},{"id":"2211.11052","title":"Convexifying Transformers: Improving optimization and understanding of transformer networks","created":"2022-11-20","cited_by_count":12},{"id":"2310.12462","title":"Unmasking Transformers: A Theoretical Approach to Data Recovery via Attention Weights","created":"2023-10-19","cited_by_count":12}],"next_cursor":null}