{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2108.07732","title":"Program Synthesis with Large Language Models","created":"2021-08-16","cited_by_count":3637},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2206.04615","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","created":"2022-06-09","cited_by_count":1998},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"2211.00593","title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","created":"2022-11-01","cited_by_count":1165},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"2301.05217","title":"Progress measures for grokking via mechanistic interpretability","created":"2023-01-12","cited_by_count":839},{"id":"2304.14997","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","created":"2023-04-28","cited_by_count":724},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1703.00810","title":"Opening the Black Box of Deep Neural Networks via Information","created":"2017-03-02","cited_by_count":503},{"id":"2201.03544","title":"The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Models","created":"2022-01-10","cited_by_count":328},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"1701.00160","title":"NIPS 2016 Tutorial: Generative Adversarial Networks","created":"2016-12-31","cited_by_count":285},{"id":"1606.05340","title":"Exponential expressivity in deep neural networks through transient chaos","created":"2016-06-16","cited_by_count":261},{"id":"2205.10343","title":"Towards Understanding Grokking: An Effective Theory of Representation Learning","created":"2022-05-20","cited_by_count":230},{"id":"1812.04754","title":"Gradient Descent Happens in a Tiny Subspace","created":"2018-12-12","cited_by_count":217},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"2202.07785","title":"Predictability and Surprise in Large Generative Models","created":"2022-02-15","cited_by_count":210},{"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":"2210.01117","title":"Omnigrok: Grokking Beyond Algorithmic Data","created":"2022-10-03","cited_by_count":146},{"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":"2303.13506","title":"The Quantization Model of Neural Scaling","created":"2023-03-23","cited_by_count":138},{"id":"2207.13243","title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","created":"2022-07-27","cited_by_count":129},{"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":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123},{"id":"2307.15936","title":"A Theory for Emergence of Complex Skills in Language Models","created":"2023-07-29","cited_by_count":113},{"id":"2210.14891","title":"Broken Neural Scaling Laws","created":"2022-10-26","cited_by_count":109},{"id":"2206.04817","title":"The Slingshot Mechanism: An Empirical Study of Adaptive Optimizers and the Grokking Phenomenon","created":"2022-06-10","cited_by_count":94},{"id":"2401.10225","title":"ChatQA: Surpassing GPT-4 on Conversational QA and RAG","created":"2024-01-18","cited_by_count":90},{"id":"1711.08856","title":"Critical Learning Periods in Deep Neural Networks","created":"2017-11-24","cited_by_count":79},{"id":"2104.07885","title":"Probing Across Time: What Does RoBERTa Know and When?","created":"2021-04-16","cited_by_count":73},{"id":"1606.00318","title":"Discovering Phase Transitions with Unsupervised Learning","created":"2016-06-01","cited_by_count":49},{"id":"2310.03789","title":"Grokking as a First Order Phase Transition in Two Layer Networks","created":"2023-10-05","cited_by_count":48},{"id":"1703.02435","title":"Unsupervised learning of phase transitions: from principal component analysis to variational autoencoders","created":"2017-03-07","cited_by_count":47},{"id":"2303.15438","title":"On the Stepwise Nature of Self-Supervised Learning","created":"2023-03-27","cited_by_count":36},{"id":"2402.03902","title":"A phase transition between positional and semantic learning in a solvable model of dot-product attention","created":"2024-02-06","cited_by_count":30},{"id":"2310.16441","title":"Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding","created":"2023-10-25","cited_by_count":25},{"id":"1904.04063","title":"Analyzing and Interpreting Neural Networks for NLP: A Report on the First BlackboxNLP Workshop","created":"2019-04-05","cited_by_count":22},{"id":"2305.18519","title":"Quantum chi-squared tomography and mutual information testing","created":"2023-05-29","cited_by_count":7},{"id":"2311.10710","title":"Machine learning phase transitions: Connections to the Fisher information","created":"2023-11-17","cited_by_count":7},{"id":"2205.12510","title":"Exact Phase Transitions in Deep Learning","created":"2022-05-25","cited_by_count":6},{"id":"1911.04633","title":"Machine learning dynamical phase transitions in complex networks","created":"2019-11-12","cited_by_count":4},{"id":"2307.02284","title":"Universal Scaling Laws of Absorbing Phase Transitions in Artificial Deep Neural Networks","created":"2023-07-05","cited_by_count":4},{"id":"1902.09216","title":"Revealing quantum chaos with machine learning","created":"2019-02-25","cited_by_count":3},{"id":"2311.09128","title":"Fast Detection of Phase Transitions with Multi-Task Learning-by-Confusion","created":"2023-11-15","cited_by_count":3},{"id":"2202.00348","title":"Learning entanglement breakdown as a phase transition by confusion","created":"2022-02-01","cited_by_count":2},{"id":"2304.06029","title":"Fluctuation based interpretable analysis scheme for quantum many-body snapshots","created":"2023-04-12","cited_by_count":2}],"next_cursor":null}