{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1806.08734","title":"On the Spectral Bias of Neural Networks","created":"2018-06-22","cited_by_count":1341},{"id":"2310.03693","title":"Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!","created":"2023-10-05","cited_by_count":1154},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1912.02178","title":"Fantastic Generalization Measures and Where to Find Them","created":"2019-12-04","cited_by_count":513},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1905.13655","title":"Implicit Regularization in Deep Matrix Factorization","created":"2019-05-31","cited_by_count":405},{"id":"2310.06452","title":"Understanding the Effects of RLHF on LLM Generalisation and Diversity","created":"2023-10-10","cited_by_count":396},{"id":"2306.09927","title":"Trained Transformers Learn Linear Models In-Context","created":"2023-06-16","cited_by_count":337},{"id":"1705.09280","title":"Implicit Regularization in Matrix Factorization","created":"2017-05-25","cited_by_count":322},{"id":"1705.07809","title":"Information-theoretic analysis of generalization capability of learning algorithms","created":"2017-05-22","cited_by_count":303},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"1806.00468","title":"Implicit Bias of Gradient Descent on Linear Convolutional Networks","created":"2018-06-01","cited_by_count":251},{"id":"1906.02226","title":"Gradient-Based Neural DAG Learning","created":"2019-06-05","cited_by_count":227},{"id":"1905.11604","title":"SGD on Neural Networks Learns Functions of Increasing Complexity","created":"2019-05-28","cited_by_count":204},{"id":"2308.09124","title":"Linearity of Relation Decoding in Transformer Language Models","created":"2023-08-17","cited_by_count":200},{"id":"1805.08522","title":"Deep learning generalizes because the parameter-function map is biased towards simple functions","created":"2018-05-22","cited_by_count":183},{"id":"2307.03576","title":"One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention","created":"2023-07-07","cited_by_count":170},{"id":"2301.11916","title":"Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning","created":"2023-01-27","cited_by_count":149},{"id":"2102.13019","title":"Investigating the Limitations of Transformers with Simple Arithmetic Tasks","created":"2021-02-25","cited_by_count":139},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"1910.01075","title":"Learning Neural Causal Models from Unknown Interventions","created":"2019-10-02","cited_by_count":113},{"id":"2007.12911","title":"Tighter risk certificates for neural networks","created":"2020-07-25","cited_by_count":112},{"id":"2109.10686","title":"Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers","created":"2021-09-22","cited_by_count":106},{"id":"2305.16130","title":"Language Models Implement Simple Word2Vec-style Vector Arithmetic","created":"2023-05-25","cited_by_count":98},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97},{"id":"2202.14037","title":"Understanding Contrastive Learning Requires Incorporating Inductive Biases","created":"2022-02-28","cited_by_count":96},{"id":"2210.14199","title":"Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Models","created":"2022-10-25","cited_by_count":84},{"id":"2305.15269","title":"Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples","created":"2023-05-24","cited_by_count":84},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76},{"id":"2302.02672","title":"Identifiability of latent-variable and structural-equation models: from linear to nonlinear","created":"2023-02-06","cited_by_count":58},{"id":"2307.02598","title":"Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation","created":"2023-07-05","cited_by_count":58},{"id":"2312.17173","title":"Non-Vacuous Generalization Bounds for Large Language Models","created":"2023-12-28","cited_by_count":53},{"id":"1911.03864","title":"Improving Transformer Models by Reordering their Sublayers","created":"2019-11-10","cited_by_count":52},{"id":"2211.11567","title":"Neural networks trained with SGD learn distributions of increasing complexity","created":"2022-11-21","cited_by_count":50},{"id":"2310.10047","title":"Improving Large Language Model Fine-tuning for Solving Math Problems","created":"2023-10-16","cited_by_count":49},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"1610.07193","title":"Simpler PAC-Bayesian Bounds for Hostile Data","created":"2016-10-23","cited_by_count":46},{"id":"2009.14786","title":"Measuring Systematic Generalization in Neural Proof Generation with Transformers","created":"2020-09-30","cited_by_count":43},{"id":"2010.13988","title":"Toward Better Generalization Bounds with Locally Elastic Stability","created":"2020-10-27","cited_by_count":42},{"id":"2203.15756","title":"Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data","created":"2022-03-29","cited_by_count":42},{"id":"2310.05327","title":"Provable Compositional Generalization for Object-Centric Learning","created":"2023-10-09","cited_by_count":41},{"id":"2211.14699","title":"A Theoretical Study of Inductive Biases in Contrastive Learning","created":"2022-11-27","cited_by_count":40},{"id":"2206.02659","title":"Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guarantees","created":"2022-06-06","cited_by_count":34},{"id":"1506.04573","title":"A New PAC-Bayesian Perspective on Domain Adaptation","created":"2015-06-15","cited_by_count":29},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29},{"id":"2307.12617","title":"Predicting Ordinary Differential Equations with Transformers","created":"2023-07-24","cited_by_count":26},{"id":"1909.11522","title":"Neural networks are a priori biased towards Boolean functions with low entropy","created":"2019-09-25","cited_by_count":24},{"id":"2311.12997","title":"Compositional Capabilities of Autoregressive Transformers: A Study on Synthetic, Interpretable Tasks","created":"2023-11-21","cited_by_count":22},{"id":"2402.04875","title":"On Provable Length and Compositional Generalization","created":"2024-02-07","cited_by_count":22},{"id":"2202.11455","title":"On PAC-Bayesian reconstruction guarantees for VAEs","created":"2022-02-23","cited_by_count":20},{"id":"2006.01338","title":"A Survey of Neural Networks and Formal Languages","created":"2020-06-02","cited_by_count":17},{"id":"2009.05552","title":"Systematic Generalization on gSCAN with Language Conditioned Embedding","created":"2020-09-11","cited_by_count":15},{"id":"2102.02976","title":"Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels","created":"2021-02-05","cited_by_count":15},{"id":"2202.10745","title":"Improving Systematic Generalization Through Modularity and Augmentation","created":"2022-02-22","cited_by_count":13},{"id":"2204.08479","title":"Inductive Biases for Object-Centric Representations in the Presence of Complex Textures","created":"2022-04-18","cited_by_count":13},{"id":"2302.08942","title":"PAC-Bayesian Generalization Bounds for Adversarial Generative Models","created":"2023-02-17","cited_by_count":13},{"id":"2106.10424","title":"On Generalization of Adversarial Imitation Learning and Beyond","created":"2021-06-19","cited_by_count":7},{"id":"2403.11834","title":"Towards Understanding the Relationship between In-context Learning and Compositional Generalization","created":"2024-03-18","cited_by_count":5},{"id":"2206.05454","title":"A General framework for PAC-Bayes Bounds for Meta-Learning","created":"2022-06-11","cited_by_count":3}],"next_cursor":null}