{"list":"other","total":87,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1611.07308","title":"Variational Graph Auto-Encoders","created":"2016-11-21","cited_by_count":1382},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2112.06905","title":"GLaM: Efficient Scaling of Language Models with Mixture-of-Experts","created":"2021-12-13","cited_by_count":897},{"id":"1803.01422","title":"DAGs with NO TEARS: Continuous Optimization for Structure Learning","created":"2018-03-04","cited_by_count":752},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"1910.01442","title":"CLEVRER: CoLlision Events for Video REpresentation and Reasoning","created":"2019-10-03","cited_by_count":484},{"id":"1705.08821","title":"Causal Effect Inference with Deep Latent-Variable Models","created":"2017-05-24","cited_by_count":410},{"id":"2005.00333","title":"XCOPA: A Multilingual Dataset for Causal Commonsense Reasoning","created":"2020-05-01","cited_by_count":333},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1702.07007","title":"Detecting causal associations in large nonlinear time series datasets","created":"2017-02-22","cited_by_count":244},{"id":"1711.00848","title":"Variational Inference of Disentangled Latent Concepts from Unlabeled Observations","created":"2017-11-02","cited_by_count":241},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211},{"id":"1804.00779","title":"Neural Autoregressive Flows","created":"2018-04-03","cited_by_count":208},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"1302.4972","title":"Causal Inference and Causal Explanation with Background Knowledge","created":"2013-02-20","cited_by_count":170},{"id":"1903.01672","title":"Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes","created":"2019-03-05","cited_by_count":166},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"1907.12087","title":"Charting the Right Manifold: Manifold Mixup for Few-shot Learning","created":"2019-07-28","cited_by_count":136},{"id":"1611.06221","title":"Foundations of Structural Causal Models with Cycles and Latent Variables","created":"2016-11-18","cited_by_count":134},{"id":"2204.07258","title":"Causal Transformer for Estimating Counterfactual Outcomes","created":"2022-04-14","cited_by_count":123},{"id":"2009.13000","title":"Interventional Few-Shot Learning","created":"2020-09-28","cited_by_count":112},{"id":"2103.03493","title":"Causal Attention for Vision-Language Tasks","created":"2021-03-05","cited_by_count":111},{"id":"2112.00826","title":"Inducing Causal Structure for Interpretable Neural Networks","created":"2021-12-01","cited_by_count":110},{"id":"2206.15475","title":"Causal Machine Learning: A Survey and Open Problems","created":"2022-06-30","cited_by_count":110},{"id":"1904.12347","title":"Domain Agnostic Learning with Disentangled Representations","created":"2019-04-28","cited_by_count":108},{"id":"1905.12506","title":"Are Disentangled Representations Helpful for Abstract Visual Reasoning?","created":"2019-05-29","cited_by_count":100},{"id":"2011.02268","title":"Causal Autoregressive Flows","created":"2020-11-04","cited_by_count":99},{"id":"2107.00793","title":"The Causal-Neural Connection: Expressiveness, Learnability, and Inference","created":"2021-07-02","cited_by_count":98},{"id":"2106.05200","title":"Independent mechanism analysis, a new concept?","created":"2021-06-09","cited_by_count":97},{"id":"2103.00887","title":"Counterfactual Zero-Shot and Open-Set Visual Recognition","created":"2021-03-01","cited_by_count":95},{"id":"2202.02195","title":"Deep End-to-end Causal Inference","created":"2022-02-04","cited_by_count":95},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91},{"id":"1909.12000","title":"CoPhy: Counterfactual Learning of Physical Dynamics","created":"2019-09-26","cited_by_count":81},{"id":"1911.10496","title":"Two Causal Principles for Improving Visual Dialog","created":"2019-11-24","cited_by_count":75},{"id":"1803.07616","title":"IntPhys: A Framework and Benchmark for Visual Intuitive Physics Reasoning","created":"2018-03-20","cited_by_count":73},{"id":"2103.01456","title":"Image-to-image Translation via Hierarchical Style Disentanglement","created":"2021-03-02","cited_by_count":63},{"id":"1804.02086","title":"Structured Disentangled Representations","created":"2018-04-06","cited_by_count":62},{"id":"1511.09249","title":"On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models","created":"2015-11-30","cited_by_count":55},{"id":"1901.08162","title":"Causal Reasoning from Meta-reinforcement Learning","created":"2019-01-23","cited_by_count":53},{"id":"1403.2150","title":"Constraint-based Causal Discovery from Multiple Interventions over Overlapping Variable Sets","created":"2014-03-10","cited_by_count":48},{"id":"2104.05441","title":"Unsuitability of NOTEARS for Causal Graph Discovery","created":"2021-04-12","cited_by_count":47},{"id":"2108.06685","title":"Vector-Decomposed Disentanglement for Domain-Invariant Object Detection","created":"2021-08-15","cited_by_count":47},{"id":"2205.05849","title":"e-CARE: a New Dataset for Exploring Explainable Causal Reasoning","created":"2022-05-12","cited_by_count":47},{"id":"2106.07635","title":"Variational Causal Networks: Approximate Bayesian Inference over Causal Structures","created":"2021-06-14","cited_by_count":43},{"id":"2102.05829","title":"Causal Inference for Time series Analysis: Problems, Methods and Evaluation","created":"2021-02-11","cited_by_count":42},{"id":"2109.04173","title":"Relating Graph Neural Networks to Structural Causal Models","created":"2021-09-09","cited_by_count":41},{"id":"2204.00607","title":"From Statistical to Causal Learning","created":"2022-04-01","cited_by_count":40},{"id":"1506.02494","title":"backShift: Learning causal cyclic graphs from unknown shift interventions","created":"2015-06-08","cited_by_count":37},{"id":"1807.03024","title":"Constraint-based Causal Discovery for Non-Linear Structural Causal Models with Cycles and Latent Confounders","created":"2018-07-09","cited_by_count":35},{"id":"2107.09846","title":"Guided Generation of Cause and Effect","created":"2021-07-21","cited_by_count":33},{"id":"2103.14232","title":"ACRE: Abstract Causal REasoning Beyond Covariation","created":"2021-03-26","cited_by_count":30},{"id":"2106.15610","title":"An Image is Worth More Than a Thousand Words: Towards Disentanglement in the Wild","created":"2021-06-29","cited_by_count":30},{"id":"2206.10591","title":"Can Foundation Models Talk Causality?","created":"2022-06-14","cited_by_count":30},{"id":"2110.06399","title":"Dynamic Inference with Neural Interpreters","created":"2021-10-12","cited_by_count":24},{"id":"2106.08314","title":"Causal Navigation by Continuous-time Neural Networks","created":"2021-06-15","cited_by_count":23},{"id":"2202.01300","title":"Causal Inference Through the Structural Causal Marginal Problem","created":"2022-02-02","cited_by_count":23},{"id":"2111.04095","title":"Iterative Causal Discovery in the Possible Presence of Latent Confounders and Selection Bias","created":"2021-11-07","cited_by_count":21},{"id":"2202.06481","title":"A Survey on Machine Learning Approaches for Modelling Intuitive Physics","created":"2022-02-14","cited_by_count":20},{"id":"2004.01167","title":"Sum-product networks: A survey","created":"2020-04-02","cited_by_count":15},{"id":"2202.08325","title":"A Data-Augmentation Is Worth A Thousand Samples: Exact Quantification From Analytical Augmented Sample Moments","created":"2022-02-16","cited_by_count":14},{"id":"1709.00199","title":"A Two-Step Disentanglement Method","created":"2017-09-01","cited_by_count":13},{"id":"2111.13936","title":"Is Causal Reasoning Harder than Probabilistic Reasoning?","created":"2021-11-27","cited_by_count":10},{"id":"2206.04620","title":"On the Generalization and Adaption Performance of Causal Models","created":"2022-06-09","cited_by_count":8},{"id":"2109.15062","title":"Towards Principled Causal Effect Estimation by Deep Identifiable Models","created":"2021-09-30","cited_by_count":4},{"id":"2202.10706","title":"Relational Causal Models with Cycles:Representation and Reasoning","created":"2022-02-22","cited_by_count":4},{"id":"2204.00762","title":"Do learned representations respect causal relationships?","created":"2022-04-02","cited_by_count":3},{"id":"1602.02383","title":"Disentangled Representations in Neural Models","created":"2016-02-07","cited_by_count":2}],"next_cursor":null}