{"list":"other","total":55,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"1510.04342","title":"Estimation and Inference of Heterogeneous Treatment Effects using Random Forests","created":"2015-10-14","cited_by_count":600},{"id":"1705.08821","title":"Causal Effect Inference with Deep Latent-Variable Models","created":"2017-05-24","cited_by_count":410},{"id":"1502.03509","title":"MADE: Masked Autoencoder for Distribution Estimation","created":"2015-02-12","cited_by_count":307},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1906.02120","title":"Adapting Neural Networks for the Estimation of Treatment Effects","created":"2019-06-05","cited_by_count":287},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"1504.01132","title":"Recursive Partitioning for Heterogeneous Causal Effects","created":"2015-04-05","cited_by_count":255},{"id":"1911.10500","title":"Causality for Machine Learning","created":"2019-11-24","cited_by_count":243},{"id":"1511.00830","title":"The Variational Fair Autoencoder","created":"2015-11-03","cited_by_count":223},{"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":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"1912.08142","title":"Causality matters in medical imaging","created":"2019-12-17","cited_by_count":193},{"id":"1511.05121","title":"Deep Kalman Filters","created":"2015-11-16","cited_by_count":166},{"id":"1901.10912","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","created":"2019-01-30","cited_by_count":158},{"id":"1709.02023","title":"CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training","created":"2017-09-06","cited_by_count":152},{"id":"1905.13662","title":"On the Fairness of Disentangled Representations","created":"2019-05-31","cited_by_count":144},{"id":"2204.07258","title":"Causal Transformer for Estimating Counterfactual Outcomes","created":"2022-04-14","cited_by_count":123},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"2402.04347","title":"The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry","created":"2024-02-06","cited_by_count":120},{"id":"2406.03689","title":"Evaluating the World Model Implicit in a Generative Model","created":"2024-06-06","cited_by_count":113},{"id":"2107.00793","title":"The Causal-Neural Connection: Expressiveness, Learnability, and Inference","created":"2021-07-02","cited_by_count":98},{"id":"2105.12907","title":"Directed Acyclic Graph Network for Conversational Emotion Recognition","created":"2021-05-27","cited_by_count":97},{"id":"1706.09141","title":"Causal Structure Learning","created":"2017-06-28","cited_by_count":84},{"id":"1804.03515","title":"Hyperparameters and Tuning Strategies for Random Forest","created":"2018-04-10","cited_by_count":84},{"id":"1701.08687","title":"Double/Debiased/Neyman Machine Learning of Treatment Effects","created":"2017-01-30","cited_by_count":76},{"id":"1310.1757","title":"A Deep and Tractable Density Estimator","created":"2013-10-07","cited_by_count":68},{"id":"2001.10652","title":"Treatment effect estimation with disentangled latent factors","created":"2020-01-29","cited_by_count":63},{"id":"1906.03485","title":"Learning Individual Causal Effects from Networked Observational Data","created":"2019-06-08","cited_by_count":56},{"id":"1701.06686","title":"Nested Markov Properties for Acyclic Directed Mixed Graphs","created":"2017-01-23","cited_by_count":39},{"id":"2006.02548","title":"Graphical Normalizing Flows","created":"2020-06-03","cited_by_count":37},{"id":"2210.13148","title":"Transformers over Directed Acyclic Graphs","created":"2022-10-24","cited_by_count":23},{"id":"2402.04779","title":"StableMask: Refining Causal Masking in Decoder-only Transformer","created":"2024-02-07","cited_by_count":20},{"id":"1903.03662","title":"A Potential Outcomes Calculus for Identifying Conditional Path-Specific Effects","created":"2019-03-08","cited_by_count":19},{"id":"1908.03918","title":"DynaNet: Neural Kalman Dynamical Model for Motion Estimation and Prediction","created":"2019-08-11","cited_by_count":13},{"id":"2311.02221","title":"Structured Neural Networks for Density Estimation and Causal Inference","created":"2023-11-03","cited_by_count":13},{"id":"2207.05899","title":"Neural Topological Ordering for Computation Graphs","created":"2022-07-13","cited_by_count":12},{"id":"2405.17151","title":"Smoke and Mirrors in Causal Downstream Tasks","created":"2024-05-27","cited_by_count":12},{"id":"1903.00402","title":"Machine learning in policy evaluation: new tools for causal inference","created":"2019-03-01","cited_by_count":10},{"id":"2103.07292","title":"VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts","created":"2021-03-12","cited_by_count":6},{"id":"2202.09875","title":"Trying to Outrun Causality with Machine Learning: Limitations of Model Explainability Techniques for Identifying Predictive Variables","created":"2022-02-20","cited_by_count":2},{"id":"2206.05175","title":"A Causal Research Pipeline and Tutorial for Psychologists and Social Scientists","created":"2022-06-10","cited_by_count":2},{"id":"2308.04365","title":"SLEM: Machine Learning for Path Modeling and Causal Inference with Super Learner Equation Modeling","created":"2023-08-08","cited_by_count":1}],"next_cursor":null}