lom_id,doi,openalex,s2_paper_id,arxiv,pmid,pmcid,acl,title,year,venue,oa_url,ingested_ts,source
arxiv:0901.2698,10.48550/arxiv.0901.2698,W1524012148,,0901.2698,,,,"On integral probability metrics, ϕ-divergences and binary classification",2009,arXiv (Cornell University),https://arxiv.org/pdf/0901.2698,2026-09-02T02:37:09Z,openalex
arxiv:0907.1815,10.48550/arxiv.0907.1815,W2120354757,,0907.1815,,,,Frustratingly Easy Domain Adaptation,2009,arXiv (Cornell University),https://arxiv.org/pdf/0907.1815,2026-09-02T02:37:09Z,openalex
arxiv:1003.0120,10.48550/arxiv.1003.0120,W2113065326,,1003.0120,,,,Learning from Logged Implicit Exploration Data,2010,arXiv (Cornell University),https://arxiv.org/pdf/1003.0120,2026-09-02T02:37:09Z,openalex
arxiv:1011.0686,10.48550/arxiv.1011.0686,W2962957031,,1011.0686,,,,A Reduction of Imitation Learning and Structured Prediction to No-Regret\n Online Learning,2010,arXiv (Cornell University),https://arxiv.org/pdf/1011.0686,2026-09-02T02:37:09Z,openalex
arxiv:1206.6389,10.48550/arxiv.1206.6389,W2112507308,,1206.6389,,,,Poisoning Attacks against Support Vector Machines,2012,arXiv (Cornell University),https://arxiv.org/pdf/1206.6389,2026-09-02T02:37:09Z,openalex
arxiv:1301.3545,10.48550/arxiv.1301.3545,W1579917626,,1301.3545,,,,Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines,2013,arXiv (Cornell University),https://arxiv.org/pdf/1301.3545,2026-09-02T02:37:09Z,openalex
arxiv:1301.3641,10.48550/arxiv.1301.3641,W1932057668,,1301.3641,,,,Training Neural Networks with Stochastic Hessian-Free Optimization,2013,arXiv (Cornell University),https://arxiv.org/pdf/1301.3641,2026-09-02T02:37:09Z,openalex
arxiv:1310.4546,10.48550/arxiv.1310.4546,W2153579005,,1310.4546,,,,Distributed Representations of Words and Phrases and their Compositionality,2013,arXiv (Cornell University),https://arxiv.org/pdf/1310.4546,2026-09-02T02:37:09Z,openalex
arxiv:1312.5602,10.48550/arxiv.1312.5602,W1757796397,,1312.5602,,,,Playing Atari with Deep Reinforcement Learning,2013,arXiv (Cornell University),https://arxiv.org/pdf/1312.5602,2026-09-02T02:37:09Z,openalex
arxiv:1312.6034,10.48550/arxiv.1312.6034,W2962851944,,1312.6034,,,,Deep Inside Convolutional Networks: Visualising Image Classification\n Models and Saliency Maps,2013,arXiv (Cornell University),https://arxiv.org/pdf/1312.6034,2026-09-02T02:37:09Z,openalex
arxiv:1312.6114,10.48550/arxiv.1312.6114,W1959608418,,1312.6114,,,,Auto-Encoding Variational Bayes,2013,UvA-DARE (University of Amsterdam),https://dare.uva.nl/personal/pure/en/publications/autoencoding-variational-bayes(cf65ba0f-d88f-4a49-8ebd-3a7fce86edd7).html,2026-09-02T02:37:09Z,openalex
arxiv:1401.0514,10.48550/arxiv.1401.0514,W1551431154,,1401.0514,,,,Structured Generative Models of Natural Source Code,2014,arXiv (Cornell University),https://arxiv.org/pdf/1401.0514,2026-09-02T02:37:09Z,openalex
arxiv:1401.4082,10.48550/arxiv.1401.4082,W2962897886,,1401.4082,,,,Stochastic Backpropagation and Approximate Inference in Deep Generative\n Models,2014,arXiv (Cornell University),https://arxiv.org/pdf/1401.4082,2026-09-02T02:37:09Z,openalex
arxiv:1406.5298,10.48550/arxiv.1406.5298,W2108501770,,1406.5298,,,,Semi-Supervised Learning with Deep Generative Models,2014,arXiv (Cornell University),https://arxiv.org/pdf/1406.5298,2026-09-02T02:37:09Z,openalex
arxiv:1409.3215,10.48550/arxiv.1409.3215,W2130942839,,1409.3215,,,,Sequence to Sequence Learning with Neural Networks,2014,arXiv (Cornell University),https://arxiv.org/pdf/1409.3215,2026-09-02T02:37:09Z,openalex
arxiv:1410.4615,10.48550/arxiv.1410.4615,W1581407678,,1410.4615,,,,Learning to Execute,2014,arXiv (Cornell University),https://arxiv.org/pdf/1410.4615,2026-09-02T02:37:09Z,openalex
arxiv:1410.8516,10.48550/arxiv.1410.8516,W1583912456,,1410.8516,,,,NICE: Non-linear Independent Components Estimation,2014,arXiv (Cornell University),https://arxiv.org/pdf/1410.8516,2026-09-02T02:37:09Z,openalex
arxiv:1412.6071,10.48550/arxiv.1412.6071,W2133319764,,1412.6071,,,,Fractional Max-Pooling,2014,arXiv (Cornell University),https://arxiv.org/pdf/1412.6071,2026-09-02T02:37:09Z,openalex
arxiv:1412.6806,10.48550/arxiv.1412.6806,W2123045220,,1412.6806,,,,Striving for Simplicity: The All Convolutional Net,2014,arXiv (Cornell University),https://arxiv.org/pdf/1412.6806,2026-09-02T02:37:09Z,openalex
arxiv:1412.6830,10.48550/arxiv.1412.6830,W1683511521,,1412.6830,,,,Learning Activation Functions to Improve Deep Neural Networks,2014,arXiv (Cornell University),https://arxiv.org/pdf/1412.6830,2026-09-02T02:37:09Z,openalex
arxiv:1412.6980,10.48550/arxiv.1412.6980,W1522301498,,1412.6980,,,,Adam: A Method for Stochastic Optimization,2014,UvA-DARE (University of Amsterdam),https://handle.uba.uva.nl/personal/pure/en/publications/adam-a-method-for-stochastic-optimization(a20791d3-1aff-464a-8544-268383c33a75).html,2026-09-02T02:37:09Z,openalex
arxiv:1502.02072,10.48550/arxiv.1502.02072,W1738019091,,1502.02072,,,,Massively Multitask Networks for Drug Discovery,2015,arXiv (Cornell University),https://arxiv.org/pdf/1502.02072,2026-09-02T02:37:09Z,openalex
arxiv:1502.02259,,,,1502.02259,,,,Contextual Markov Decision Processes,2015,,https://arxiv.org/abs/1502.02259,2026-09-02T02:23:34Z,paper
arxiv:1502.05477,10.48550/arxiv.1502.05477,W1771410628,,1502.05477,,,,Trust Region Policy Optimization,2015,arXiv (Cornell University),https://arxiv.org/pdf/1502.05477,2026-09-02T02:37:09Z,openalex
arxiv:1503.01445,10.48550/arxiv.1503.01445,W2150854591,,1503.01445,,,,Toxicity Prediction using Deep Learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1503.01445,2026-09-02T02:37:09Z,openalex
arxiv:1503.02531,10.48550/arxiv.1503.02531,W1821462560,,1503.02531,,,,Distilling the Knowledge in a Neural Network,2015,arXiv (Cornell University),https://arxiv.org/pdf/1503.02531,2026-09-02T02:37:09Z,openalex
arxiv:1503.03585,10.48550/arxiv.1503.03585,W2129069237,,1503.03585,,,,Deep Unsupervised Learning using Nonequilibrium Thermodynamics,2015,arXiv (Cornell University),https://arxiv.org/pdf/1503.03585,2026-09-02T02:37:09Z,openalex
arxiv:1504.00325,10.48550/arxiv.1504.00325,W1889081078,,1504.00325,,,,Microsoft COCO Captions: Data Collection and Evaluation Server,2015,arXiv (Cornell University),https://arxiv.org/pdf/1504.00325,2026-09-02T02:37:09Z,openalex
arxiv:1505.00521,10.48550/arxiv.1505.00521,W2204302769,,1505.00521,,,,Reinforcement Learning Neural Turing Machines - Revised,2015,arXiv (Cornell University),https://arxiv.org/pdf/1505.00521,2026-09-02T02:37:09Z,openalex
arxiv:1505.00853,10.48550/arxiv.1505.00853,W1921523184,,1505.00853,,,,Empirical Evaluation of Rectified Activations in Convolutional Network,2015,arXiv (Cornell University),https://arxiv.org/pdf/1505.00853,2026-09-02T02:37:09Z,openalex
arxiv:1506.02142,10.48550/arxiv.1506.02142,W2964059111,,1506.02142,,,,Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1506.02142,2026-09-02T02:37:09Z,openalex
arxiv:1506.02438,10.48550/arxiv.1506.02438,W1191599655,,1506.02438,,,,High-Dimensional Continuous Control Using Generalized Advantage Estimation,2015,arXiv (Cornell University),https://arxiv.org/pdf/1506.02438,2026-09-02T02:37:09Z,openalex
arxiv:1507.00210,10.48550/arxiv.1507.00210,W1915968771,,1507.00210,,,,Natural Neural Networks,2015,arXiv (Cornell University),https://arxiv.org/pdf/1507.00210,2026-09-02T02:37:09Z,openalex
arxiv:1508.03411,10.48550/arxiv.1508.03411,W2249314671,,1508.03411,,,,Emphatic TD Bellman Operator is a Contraction,2015,arXiv (Cornell University),https://arxiv.org/pdf/1508.03411,2026-09-02T02:37:09Z,openalex
arxiv:1509.02971,10.48550/arxiv.1509.02971,W2173248099,,1509.02971,,,,Continuous control with deep reinforcement learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1509.02971,2026-09-02T02:37:09Z,openalex
arxiv:1509.05172,10.48550/arxiv.1509.05172,W2964298957,,1509.05172,,,,Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis,2015,arXiv (Cornell University),https://arxiv.org/pdf/1509.05172,2026-09-02T02:37:09Z,openalex
arxiv:1511.01432,10.48550/arxiv.1511.01432,W2170973209,,1511.01432,,,,Semi-supervised Sequence Learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1511.01432,2026-09-02T02:37:09Z,openalex
arxiv:1511.03722,10.48550/arxiv.1511.03722,W2234859443,,1511.03722,,,,Doubly Robust Off-policy Value Evaluation for Reinforcement Learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1511.03722,2026-09-02T02:37:09Z,openalex
arxiv:1511.06295,10.48550/arxiv.1511.06295,W2584377191,,1511.06295,,,,Policy Distillation,2015,arXiv (Cornell University),https://arxiv.org/pdf/1511.06295,2026-09-02T02:37:09Z,openalex
arxiv:1511.06342,10.48550/arxiv.1511.06342,W2174786457,,1511.06342,,,,Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning,2015,arXiv (Cornell University),https://arxiv.org/pdf/1511.06342,2026-09-02T02:37:09Z,openalex
arxiv:1511.07289,10.48550/arxiv.1511.07289,W2176412452,,1511.07289,,,,Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs),2016,arXiv (Cornell University),https://arxiv.org/pdf/1511.07289,2026-09-02T02:34:27Z,openalex
arxiv:1511.08228,10.48550/arxiv.1511.08228,W2173051530,,1511.08228,,,,Neural GPUs Learn Algorithms,2015,arXiv (Cornell University),https://arxiv.org/pdf/1511.08228,2026-09-02T02:37:09Z,openalex
arxiv:1512.03385,10.48550/arxiv.1512.03385,W2949650786,,1512.03385,,,,Deep Residual Learning for Image Recognition,2015,arXiv (Cornell University),https://arxiv.org/pdf/1512.03385,2026-09-02T02:37:09Z,openalex
arxiv:1601.06759,10.48550/arxiv.1601.06759,W2267126114,,1601.06759,,,,Pixel Recurrent Neural Networks,2016,arXiv (Cornell University),https://arxiv.org/pdf/1601.06759,2026-09-02T02:37:09Z,openalex
arxiv:1603.01121,10.48550/arxiv.1603.01121,W2291986326,,1603.01121,,,,Deep Reinforcement Learning from Self-Play in Imperfect-Information Games,2016,arXiv (Cornell University),https://arxiv.org/pdf/1603.01121,2026-09-02T02:37:09Z,openalex
arxiv:1603.06744,10.48550/arxiv.1603.06744,W2304240348,,1603.06744,,,,Latent Predictor Networks for Code Generation,2016,arXiv (Cornell University),https://arxiv.org/pdf/1603.06744,2026-09-02T02:37:09Z,openalex
arxiv:1604.06174,10.48550/arxiv.1604.06174,W2338908902,,1604.06174,,,,Training Deep Nets with Sublinear Memory Cost,2016,arXiv (Cornell University),https://arxiv.org/pdf/1604.06174,2026-09-02T02:37:09Z,openalex
arxiv:1604.07316,10.48550/arxiv.1604.07316,W2342840547,,1604.07316,,,,End to End Learning for Self-Driving Cars,2016,arXiv (Cornell University),https://arxiv.org/pdf/1604.07316,2026-09-02T02:37:09Z,openalex
arxiv:1605.06431,10.48550/arxiv.1605.06431,W2541674938,,1605.06431,,,,Residual Networks Behave Like Ensembles of Relatively Shallow Networks,2016,arXiv (Cornell University),https://arxiv.org/pdf/1605.06431,2026-09-02T02:37:09Z,openalex
arxiv:1605.07146,10.48550/arxiv.1605.07146,W2401231614,,1605.07146,,,,Wide Residual Networks,2016,arXiv (Cornell University),https://arxiv.org/pdf/1605.07146,2026-09-02T02:37:09Z,openalex