{"list":"other","total":61,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1607.01719","title":"Deep CORAL: Correlation Alignment for Deep Domain Adaptation","created":"2016-07-06","cited_by_count":1200},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2003.00688","title":"Out-of-Distribution Generalization via Risk Extrapolation (REx)","created":"2020-03-02","cited_by_count":742},{"id":"2212.07677","title":"Transformers learn in-context by gradient descent","created":"2022-12-15","cited_by_count":732},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"2211.15661","title":"What learning algorithm is in-context learning? Investigations with linear models","created":"2022-11-28","cited_by_count":684},{"id":"1301.2115","title":"Domain Generalization via Invariant Feature Representation","created":"2013-01-10","cited_by_count":623},{"id":"1501.01332","title":"Causal inference using invariant prediction: identification and confidence intervals","created":"2015-01-06","cited_by_count":536},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2204.02937","title":"Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations","created":"2022-04-06","cited_by_count":381},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1807.01622","title":"Neural Processes","created":"2018-07-04","cited_by_count":311},{"id":"1603.04779","title":"Revisiting Batch Normalization For Practical Domain Adaptation","created":"2016-03-15","cited_by_count":288},{"id":"1901.05761","title":"Attentive Neural Processes","created":"2019-01-17","cited_by_count":283},{"id":"2104.09937","title":"Gradient Matching for Domain Generalization","created":"2021-04-20","cited_by_count":258},{"id":"2006.07500","title":"Domain Generalization using Causal Matching","created":"2020-06-12","cited_by_count":225},{"id":"2106.06607","title":"Invariance Principle Meets Information Bottleneck for Out-of-Distribution Generalization","created":"2021-06-11","cited_by_count":220},{"id":"2002.04692","title":"Invariant Risk Minimization Games","created":"2020-02-11","cited_by_count":188},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186},{"id":"2001.00677","title":"Improve Unsupervised Domain Adaptation with Mixup Training","created":"2020-01-03","cited_by_count":185},{"id":"2007.02931","title":"Adaptive Risk Minimization: Learning to Adapt to Domain Shift","created":"2020-07-06","cited_by_count":183},{"id":"1711.07910","title":"Domain Generalization by Marginal Transfer Learning","created":"2017-11-21","cited_by_count":180},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"1807.08479","title":"Domain Generalization via Conditional Invariant Representation","created":"2018-07-23","cited_by_count":146},{"id":"2210.11369","title":"On Feature Learning in the Presence of Spurious Correlations","created":"2022-10-20","cited_by_count":145},{"id":"2102.10395","title":"On Calibration and Out-of-domain Generalization","created":"2021-02-20","cited_by_count":134},{"id":"2009.00329","title":"Learning explanations that are hard to vary","created":"2020-09-01","cited_by_count":132},{"id":"2003.09772","title":"Invariant Rationalization","created":"2020-03-22","cited_by_count":131},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104},{"id":"2211.14238","title":"Wild-Time: A Benchmark of in-the-Wild Distribution Shift over Time","created":"2022-11-25","cited_by_count":90},{"id":"2106.03721","title":"OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization","created":"2021-06-07","cited_by_count":86},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66},{"id":"2105.06422","title":"Causally motivated Shortcut Removal Using Auxiliary Labels","created":"2021-05-13","cited_by_count":55},{"id":"2201.12919","title":"Provable Domain Generalization via Invariant-Feature Subspace Recovery","created":"2022-01-30","cited_by_count":32},{"id":"2106.09913","title":"Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments","created":"2021-06-18","cited_by_count":30},{"id":"2203.09978","title":"WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series","created":"2022-03-18","cited_by_count":30},{"id":"2305.16704","title":"A Closer Look at In-Context Learning under Distribution Shifts","created":"2023-05-26","cited_by_count":25},{"id":"2307.09933","title":"Spuriosity Didn't Kill the Classifier: Using Invariant Predictions to Harness Spurious Features","created":"2023-07-19","cited_by_count":21},{"id":"2010.07167","title":"Learning Robust Models Using The Principle of Independent Causal Mechanisms","created":"2020-10-14","cited_by_count":18},{"id":"2303.02343","title":"What Is Missing in IRM Training and Evaluation? Challenges and Solutions","created":"2023-03-04","cited_by_count":10},{"id":"2305.19402","title":"Contextual Vision Transformers for Robust Representation Learning","created":"2023-05-30","cited_by_count":10},{"id":"2211.15724","title":"Malign Overfitting: Interpolation Can Provably Preclude Invariance","created":"2022-11-28","cited_by_count":6},{"id":"2210.04303","title":"Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap","created":"2022-10-09","cited_by_count":5},{"id":"2212.11342","title":"Target Conditioned Representation Independence (TCRI); From Domain-Invariant to Domain-General Representations","created":"2022-12-21","cited_by_count":3}],"next_cursor":null}