{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1506.03134","title":"Pointer Networks","created":"2015-06-09","cited_by_count":895},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"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":"2010.16011","title":"POMO: Policy Optimization with Multiple Optima for Reinforcement Learning","created":"2020-10-30","cited_by_count":348},{"id":"2103.16716","title":"BASE Layers: Simplifying Training of Large, Sparse Models","created":"2021-03-30","cited_by_count":320},{"id":"1312.4314","title":"Learning Factored Representations in a Deep Mixture of Experts","created":"2013-12-16","cited_by_count":278},{"id":"1906.01227","title":"An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem","created":"2019-06-04","cited_by_count":269},{"id":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2106.04426","title":"Hash Layers For Large Sparse Models","created":"2021-06-08","cited_by_count":237},{"id":"2302.08224","title":"DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization","created":"2023-02-16","cited_by_count":221},{"id":"2402.01739","title":"OpenMoE: An Early Effort on Open Mixture-of-Experts Language Models","created":"2024-01-29","cited_by_count":187},{"id":"1810.00337","title":"Learning to Perform Local Rewriting for Combinatorial Optimization","created":"2018-09-30","cited_by_count":185},{"id":"2402.07871","title":"Scaling Laws for Fine-Grained Mixture of Experts","created":"2024-02-12","cited_by_count":173},{"id":"1912.05784","title":"Learning Improvement Heuristics for Solving Routing Problems","created":"2019-12-12","cited_by_count":164},{"id":"2012.10658","title":"Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instances","created":"2020-12-19","cited_by_count":162},{"id":"2209.01667","title":"A Review of Sparse Expert Models in Deep Learning","created":"2022-09-04","cited_by_count":148},{"id":"2310.07985","title":"Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization","created":"2023-10-12","cited_by_count":142},{"id":"2210.04123","title":"DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems","created":"2022-10-08","cited_by_count":129},{"id":"2012.10384","title":"Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* Neighborhood","created":"2020-11-23","cited_by_count":125},{"id":"2205.13209","title":"Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization","created":"2022-05-26","cited_by_count":119},{"id":"1911.09539","title":"Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem","created":"2019-11-21","cited_by_count":117},{"id":"2107.04139","title":"Learning to Delegate for Large-scale Vehicle Routing","created":"2021-07-08","cited_by_count":109},{"id":"2110.07983","title":"NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problem","created":"2021-10-15","cited_by_count":103},{"id":"2004.01608","title":"Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learning","created":"2020-04-03","cited_by_count":100},{"id":"2102.11756","title":"Deep Policy Dynamic Programming for Vehicle Routing Problems","created":"2021-02-23","cited_by_count":94},{"id":"2106.11113","title":"Matrix Encoding Networks for Neural Combinatorial Optimization","created":"2021-06-21","cited_by_count":91},{"id":"2310.18264","title":"Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt","created":"2023-10-27","cited_by_count":81},{"id":"2309.14032","title":"DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization","created":"2023-09-25","cited_by_count":78},{"id":"2306.17100","title":"RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark","created":"2023-06-29","cited_by_count":71},{"id":"2305.19587","title":"Towards Omni-generalizable Neural Methods for Vehicle Routing Problems","created":"2023-05-31","cited_by_count":69},{"id":"2210.07686","title":"Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation","created":"2022-10-14","cited_by_count":62},{"id":"2308.14104","title":"Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy","created":"2023-08-27","cited_by_count":62},{"id":"2210.03475","title":"Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization","created":"2022-10-07","cited_by_count":58},{"id":"2303.10538","title":"Unsupervised Learning for Solving the Travelling Salesman Problem","created":"2023-03-19","cited_by_count":58},{"id":"2403.07041","title":"Ant Colony Sampling with GFlowNets for Combinatorial Optimization","created":"2024-03-11","cited_by_count":53},{"id":"2402.16891","title":"Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization","created":"2024-02-23","cited_by_count":50},{"id":"2106.00305","title":"Independent Prototype Propagation for Zero-Shot Compositionality","created":"2021-06-01","cited_by_count":42},{"id":"2311.13569","title":"Combinatorial Optimization with Policy Adaptation using Latent Space Search","created":"2023-11-13","cited_by_count":41},{"id":"2110.10942","title":"Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness","created":"2021-10-21","cited_by_count":35},{"id":"2402.14048","title":"PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization","created":"2024-02-21","cited_by_count":35},{"id":"2305.03288","title":"Demystifying Softmax Gating Function in Gaussian Mixture of Experts","created":"2023-05-05","cited_by_count":33},{"id":"2110.02629","title":"Deep Reinforcement Learning for Solving the Heterogeneous Capacitated Vehicle Routing Problem","created":"2021-10-06","cited_by_count":31},{"id":"2309.13850","title":"Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts","created":"2023-09-25","cited_by_count":29},{"id":"2204.03236","title":"Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum","created":"2022-04-07","cited_by_count":27},{"id":"2303.00466","title":"ASP: Learn a Universal Neural Solver!","created":"2023-03-01","cited_by_count":27},{"id":"2206.00787","title":"On the Generalization of Neural Combinatorial Optimization Heuristics","created":"2022-06-01","cited_by_count":24},{"id":"2404.11677","title":"Cross-Problem Learning for Solving Vehicle Routing Problems","created":"2024-04-17","cited_by_count":24},{"id":"2306.02688","title":"Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization","created":"2023-06-05","cited_by_count":23},{"id":"2206.02107","title":"Interpretable Mixture of Experts","created":"2022-06-05","cited_by_count":17},{"id":"2310.15195","title":"Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement","created":"2023-10-22","cited_by_count":13},{"id":"2302.13797","title":"Learning Large Neighborhood Search for Vehicle Routing in Airport Ground Handling","created":"2023-02-27","cited_by_count":10},{"id":"2303.02442","title":"Neural Airport Ground Handling","created":"2023-03-04","cited_by_count":7}],"next_cursor":null}