{"list":"other","total":69,"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":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1706.02216","title":"Inductive Representation Learning on Large Graphs","created":"2017-06-07","cited_by_count":6320},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1901.00596","title":"A Comprehensive Survey on Graph Neural Networks","created":"2019-01-03","cited_by_count":2919},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1609.03499","title":"WaveNet: A Generative Model for Raw Audio","created":"2016-09-12","cited_by_count":1722},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"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":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"1807.02811","title":"A Tutorial on Bayesian Optimization","created":"2018-07-08","cited_by_count":744},{"id":"1803.08475","title":"Attention, Learn to Solve Routing Problems!","created":"2018-03-22","cited_by_count":656},{"id":"1811.06128","title":"Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon","created":"2018-11-15","cited_by_count":623},{"id":"1611.09940","title":"Neural Combinatorial Optimization with Reinforcement Learning","created":"2016-11-29","cited_by_count":608},{"id":"1703.00443","title":"OptNet: Differentiable Optimization as a Layer in Neural Networks","created":"2017-03-01","cited_by_count":599},{"id":"1911.10635","title":"Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms","created":"2019-11-24","cited_by_count":567},{"id":"1704.01665","title":"Learning Combinatorial Optimization Algorithms over Graphs","created":"2017-04-05","cited_by_count":561},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1910.12430","title":"Differentiable Convex Optimization Layers","created":"2019-10-28","cited_by_count":465},{"id":"1710.10571","title":"Certifying Some Distributional Robustness with Principled Adversarial Training","created":"2017-10-29","cited_by_count":337},{"id":"1810.08750","title":"Learning Models with Uniform Performance via Distributionally Robust Optimization","created":"2018-10-20","cited_by_count":335},{"id":"1802.04240","title":"Reinforcement Learning for Solving the Vehicle Routing Problem","created":"2018-02-12","cited_by_count":333},{"id":"1906.01629","title":"Exact Combinatorial Optimization with Graph Convolutional Neural Networks","created":"2019-06-04","cited_by_count":318},{"id":"1505.05116","title":"Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations","created":"2015-05-19","cited_by_count":291},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"1809.05504","title":"Melding the Data-Decisions Pipeline: Decision-Focused Learning for Combinatorial Optimization","created":"2018-09-14","cited_by_count":227},{"id":"2103.16378","title":"End-to-End Constrained Optimization Learning: A Survey","created":"2021-03-30","cited_by_count":157},{"id":"1402.5481","title":"From Predictive to Prescriptive Analytics","created":"2014-02-22","cited_by_count":143},{"id":"2307.13565","title":"Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities","created":"2023-07-25","cited_by_count":130},{"id":"1811.08359","title":"Strong mixed-integer programming formulations for trained neural networks","created":"2018-11-20","cited_by_count":115},{"id":"2402.10172","title":"OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models","created":"2024-02-15","cited_by_count":109},{"id":"1909.10461","title":"Predicting AC Optimal Power Flows: Combining Deep Learning and Lagrangian Dual Methods","created":"2019-09-19","cited_by_count":94},{"id":"1401.0212","title":"Data-Driven Robust Optimization","created":"2013-12-31","cited_by_count":85},{"id":"2306.10374","title":"A Survey of Contextual Optimization Methods for Decision Making under Uncertainty","created":"2023-06-17","cited_by_count":82},{"id":"2007.13982","title":"Distributionally Robust Losses for Latent Covariate Mixtures","created":"2020-07-28","cited_by_count":58},{"id":"1905.11488","title":"Generalization Bounds in the Predict-then-Optimize Framework","created":"2019-05-27","cited_by_count":54},{"id":"1910.14448","title":"DeepOPF: A Deep Neural Network Approach for Security-Constrained DC Optimal Power Flow","created":"2019-10-30","cited_by_count":50},{"id":"2205.14210","title":"MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solvers","created":"2022-05-27","cited_by_count":49},{"id":"1705.10883","title":"Optimization of Tree Ensembles","created":"2017-05-30","cited_by_count":26},{"id":"2003.13676","title":"Deep reinforcement learning for large-scale epidemic control","created":"2020-03-30","cited_by_count":16},{"id":"2507.21502","title":"Large Language Models for Supply Chain Decisions","created":"2025-07-29","cited_by_count":13},{"id":"2401.03451","title":"Optimization Over Trained Neural Networks: Taking a Relaxing Walk","created":"2024-01-07","cited_by_count":10},{"id":"2405.15251","title":"Learning to optimize: A tutorial for continuous and mixed-integer optimization","created":"2024-05-24","cited_by_count":8},{"id":"2112.02215","title":"Deep Policy Iteration with Integer Programming for Inventory Management","created":"2021-12-04","cited_by_count":6},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6},{"id":"2207.02937","title":"Learning Optimal Solutions via an LSTM-Optimization Framework","created":"2022-07-06","cited_by_count":6},{"id":"2602.19439","title":"OptiRepair: Closed-Loop Diagnosis and Repair of Supply Chain Optimization Models with LLM Agents","created":"2026-02-23","cited_by_count":5},{"id":"2311.06972","title":"An Expandable Machine Learning-Optimization Framework to Sequential Decision-Making","created":"2023-11-12","cited_by_count":4},{"id":"2510.24013","title":"Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Scheduling","created":"2025-10-28","cited_by_count":4},{"id":"2101.08746","title":"Chance-Constrained Optimization under Limited Distributional Information: A Review of Reformulations Based on Sampling and Distributional Robustness","created":"2021-01-21","cited_by_count":3},{"id":"2508.21622","title":"Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study","created":"2025-08-29","cited_by_count":3},{"id":"1702.00880","title":"Combining Progressive Hedging with a Frank-Wolfe Method to Compute Lagrangian Dual Bounds in Stochastic Mixed-Integer Programming","created":"2017-02-03","cited_by_count":2},{"id":"1906.03513","title":"Adaptive Two-stage Stochastic Programming with an Analysis on Capacity Expansion Planning Problem","created":"2019-06-08","cited_by_count":2},{"id":"2102.11814","title":"A Multi-Stage Stochastic Programming Approach to Epidemic Resource Allocation with Equity Considerations","created":"2021-02-23","cited_by_count":2},{"id":"2402.13380","title":"Toward TransfORmers: Revolutionizing the Solution of Mixed Integer Programs with Transformers","created":"2024-02-20","cited_by_count":2},{"id":"2105.01698","title":"Model-Free Incremental Adaptive Dynamic Programming Based Approximate Robust Optimal Regulation","created":"2021-05-04","cited_by_count":1},{"id":"2509.22981","title":"MDP modeling for multi-stage stochastic programs","created":"2025-09-26","cited_by_count":1},{"id":"2510.16969","title":"A Multi-echelon Demand-driven Supply Chain Model for Proactive Optimal Control of Epidemics: Insights from a COVID-19 Study","created":"2025-10-19","cited_by_count":1}],"next_cursor":null}