{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/mixture-of-experts/papers/13","list_of":"/task/mixture-of-experts","task":"Mixture-of-Experts","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":13,"pages_in_order":14,"rows_per_page":100,"rows":[1201,1300],"of":1312,"counts":{"archive_papers_tagged":1312,"with_a_code_link":516,"where_syntology_ran_a_sample":216,"not_listed_spam_title":0,"listed":1312,"listed_where_code_ran":216,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":184,"every_run_a_failure_of_syntologys_instrument":32,"listed_with_a_run_with_no_instrument_failure":184,"listed_every_run_a_failure_of_syntologys_instrument":32,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/mixture-of-experts","prev":"/task/mixture-of-experts/papers/12","next":"/task/mixture-of-experts/papers/14","papers":[{"url":null,"slug":"beyond-distillation-task-level-mixture-of","title":"Beyond Distillation: Task-level Mixture-of-Experts for Efficient Inference","date":"2021-09-24","arxiv_id":"2110.03742","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-gradient-estimation-with-balanced","title":"Unbiased Gradient Estimation with Balanced Assignments for Mixtures of Experts","date":"2021-09-24","arxiv_id":"2109.11817","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparse-mlp-a-fully-mlp-architecture-with","title":"Cross-token Modeling with Conditional Computation","date":"2021-09-05","arxiv_id":"2109.02008","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalised-federated-learning-a","title":"Personalised Federated Learning: A Combinational Approach","date":"2021-08-22","arxiv_id":"2108.09618","repositories_listed":0,"syntology":null},{"url":null,"slug":"spmoe-generate-multiple-pattern-aware-outputs","title":"SPMoE: Generate Multiple Pattern-Aware Outputs with Sparse Pattern Mixture of Experts","date":"2021-08-17","arxiv_id":"2108.07535","repositories_listed":0,"syntology":null},{"url":null,"slug":"airex-neural-network-based-approach-for-air","title":"AIREX: Neural Network-based Approach for Air Quality Inference in Unmonitored Cities","date":"2021-08-16","arxiv_id":"2108.07120","repositories_listed":0,"syntology":null},{"url":null,"slug":"strength-in-numbers-averaging-and-clustering","title":"Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing","date":"2021-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"expertrank-a-multi-level-coarse-grained","title":"ExpertRank: A Multi-level Coarse-grained Expert-based Listwise Ranking Loss","date":"2021-07-29","arxiv_id":"2107.13752","repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-mixture-of-experts-1","title":"Federated Mixture of Experts","date":"2021-07-14","arxiv_id":"2107.06724","repositories_listed":0,"syntology":null},{"url":null,"slug":"adaspeech-3-adaptive-text-to-speech-for","title":"AdaSpeech 3: Adaptive Text to Speech for Spontaneous Style","date":"2021-07-06","arxiv_id":"2107.02530","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-component-interactions-in-two-stage","title":"On component interactions in two-stage recommender systems","date":"2021-06-28","arxiv_id":"2106.14979","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixtures-of-deep-neural-experts-for-automated","title":"Mixtures of Deep Neural Experts for Automated Speech Scoring","date":"2021-06-23","arxiv_id":"2106.12475","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-multi-objective-policy-optimization-as-a","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning","date":"2021-06-15","arxiv_id":"2106.08199","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-document-sketching-generating","title":"Automatic Document Sketching: Generating Drafts from Analogous Texts","date":"2021-06-14","arxiv_id":"2106.07192","repositories_listed":0,"syntology":null},{"url":null,"slug":"adatag-multi-attribute-value-extraction-from","title":"AdaTag: Multi-Attribute Value Extraction from Product Profiles with Adaptive Decoding","date":"2021-06-04","arxiv_id":"2106.02318","repositories_listed":0,"syntology":null},{"url":null,"slug":"gemnet-effective-gated-gazetteer","title":"GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input","date":"2021-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-sparse-expert-models-and-beyond","title":"M6-T: Exploring Sparse Expert Models and Beyond","date":"2021-05-31","arxiv_id":"2105.15082","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-expansion-using-back-translation-and","title":"Data Expansion using Back Translation and Paraphrasing for Hate Speech Detection","date":"2021-05-25","arxiv_id":"2106.04681","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-elm-based-experts-with-trainable","title":"Mixture of ELM based experts with trainable gating network","date":"2021-05-25","arxiv_id":"2105.11706","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalizable-person-re-identification-with","title":"Generalizable Person Re-identification with Relevance-aware Mixture of Experts","date":"2021-05-19","arxiv_id":"2105.09156","repositories_listed":0,"syntology":null},{"url":null,"slug":"mtnet-a-multi-task-neural-network-for-on","title":"MTNet: A Multi-Task Neural Network for On-Field Calibration of Low-Cost Air Monitoring Sensors","date":"2021-05-10","arxiv_id":"2105.04425","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-non-asymptotic-model-selection-in-block","title":"Non-asymptotic model selection in block-diagonal mixture of polynomial experts models","date":"2021-04-18","arxiv_id":"2104.08959","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-topic-rumor-detection-using-topic","title":"Cross-Topic Rumor Detection using Topic-Mixtures","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":"/paper/multi-gat-a-graphical-attention-based","slug":"multi-gat-a-graphical-attention-based","title":"Multi-GAT: A Graphical Attention-based Hierarchical Multimodal Representation Learning Approach for Human Activity Recognition","date":"2021-04-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"imitation-learning-from-mpc-for-quadrupedal","title":"Imitation Learning from MPC for Quadrupedal Multi-Gait Control","date":"2021-03-26","arxiv_id":"2103.14331","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-autonomous-negotiating-agent-framework","title":"An Autonomous Negotiating Agent Framework with Reinforcement Learning Based Strategies and Adaptive Strategy Switching Mechanism","date":"2021-02-06","arxiv_id":"2102.03588","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-cluster-classify-regress-model","title":"A Novel Cluster Classify Regress Model Predictive Controller Formulation; CCR-MPC","date":"2021-01-15","arxiv_id":"2101.07655","repositories_listed":0,"syntology":null},{"url":null,"slug":"preferential-mixture-of-experts-interpretable","title":"Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible","date":"2021-01-13","arxiv_id":"2101.05360","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-routing-strategies-for-multilingual","title":"Exploring Routing Strategies for Multilingual Mixture-of-Experts Models","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"federated-learning-using-mixture-of-experts","title":"Federated learning using mixture of experts","date":"2021-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"gated-ensemble-of-spatio-temporal-mixture-of","title":"Gated Ensemble of Spatio-temporal Mixture of Experts for Multi-task Learning in Ride-hailing System","date":"2020-12-31","arxiv_id":"2012.15408","repositories_listed":0,"syntology":null},{"url":null,"slug":"channel-gain-cartography-via-mixture-of","title":"Channel Gain Cartography via Mixture of Experts","date":"2020-12-08","arxiv_id":"2012.04290","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-similarity-based-bayesian-mixture-of","title":"A similarity-based Bayesian mixture-of-experts model","date":"2020-12-03","arxiv_id":"2012.02130","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-transduction-for-multilingual-lexical","title":"Neural Transduction for Multilingual Lexical Translation","date":"2020-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dadnn-multi-scene-ctr-prediction-via-domain","title":"DADNN: Multi-Scene CTR Prediction via Domain-Aware Deep Neural Network","date":"2020-11-24","arxiv_id":"2011.11938","repositories_listed":0,"syntology":null},{"url":null,"slug":"action-concept-grounding-network-for-1","title":"Modular Action Concept Grounding in Semantic Video Prediction","date":"2020-11-23","arxiv_id":"2011.11201","repositories_listed":0,"syntology":null},{"url":null,"slug":"nested-mixture-of-experts-cooperative-and","title":"Nested Mixture of Experts: Cooperative and Competitive Learning of Hybrid Dynamical System","date":"2020-11-20","arxiv_id":"2011.10605","repositories_listed":0,"syntology":null},{"url":null,"slug":"rtm-ensemble-learning-results-at-quality","title":"RTM Ensemble Learning Results at Quality Estimation Task","date":"2020-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-clustering-using-persistent-homology","title":"Memory Clustering using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-starts","date":"2020-10-02","arxiv_id":"2010.01024","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-l-1-oracle-inequality-for-the-lasso-in","title":"Non-asymptotic oracle inequalities for the Lasso in high-dimensional mixture of experts","date":"2020-09-22","arxiv_id":"2009.10622","repositories_listed":0,"syntology":null},{"url":null,"slug":"double-wing-mixture-of-experts-for-streaming","title":"Double-Wing Mixture of Experts for Streaming Recommendations","date":"2020-09-14","arxiv_id":"2009.06327","repositories_listed":0,"syntology":null},{"url":null,"slug":"aphasic-speech-recognition-using-a-mixture-of","title":"Aphasic Speech Recognition using a Mixture of Speech Intelligibility Experts","date":"2020-08-25","arxiv_id":"2008.10788","repositories_listed":0,"syntology":null},{"url":null,"slug":"biased-mixtures-of-experts-enabling-computer","title":"Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations","date":"2020-08-21","arxiv_id":"2008.09662","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixcaps-a-capsule-network-based-mixture-of","title":"MIXCAPS: A Capsule Network-based Mixture of Experts for Lung Nodule Malignancy Prediction","date":"2020-08-13","arxiv_id":"2008.06072","repositories_listed":0,"syntology":null},{"url":null,"slug":"team-deep-mixture-of-experts-for-distributed","title":"Team Deep Mixture of Experts for Distributed Power Control","date":"2020-07-28","arxiv_id":"2007.14147","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mixture-of-h-1-heads-is-better-than-h-heads-1","title":"A Mixture of h - 1 Heads is Better than h Heads","date":"2020-07-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"model-agnostic-combination-for-ensemble","title":"Model Agnostic Combination for Ensemble Learning","date":"2020-06-16","arxiv_id":"2006.09025","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-efficient-application-of-bayesian","title":"An efficient application of Bayesian optimization to an industrial MDO framework for aircraft design","date":"2020-06-12","arxiv_id":"2006.08434","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-fast-deep-mixtures-of-gaussian-process","title":"Fast Deep Mixtures of Gaussian Process Experts","date":"2020-06-11","arxiv_id":"2006.13309","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-tree-architecture-of-lstm-networks-for","title":"A Tree Architecture of LSTM Networks for Sequential Regression with Missing Data","date":"2020-05-22","arxiv_id":"2005.11353","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mixture-of-h-1-heads-is-better-than-h-heads","title":"A Mixture of $h-1$ Heads is Better than $h$ Heads","date":"2020-05-13","arxiv_id":"2005.06537","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-based-digital-twin-for","title":"Machine learning based digital twin for dynamical systems with multiple time-scales","date":"2020-05-12","arxiv_id":"2005.05862","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-policy-reuse-using-deep-mixture","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","date":"2020-02-29","arxiv_id":"2003.00203","repositories_listed":0,"syntology":null},{"url":null,"slug":"off-policy-maximum-entropy-reinforcement","title":"Off-policy Maximum Entropy Reinforcement Learning : Soft Actor-Critic with Advantage Weighted Mixture Policy(SAC-AWMP)","date":"2020-02-07","arxiv_id":"2002.02829","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-data-server-a-large-scale-search","title":"Neural Data Server: A Large-Scale Search Engine for Transfer Learning Data","date":"2020-01-09","arxiv_id":"2001.02799","repositories_listed":0,"syntology":null},{"url":null,"slug":"gla-in-mediaeval-2018-emotional-impact-of","title":"GLA in MediaEval 2018 Emotional Impact of Movies Task","date":"2019-11-27","arxiv_id":"1911.12361","repositories_listed":0,"syntology":null},{"url":null,"slug":"cler-cross-task-learning-with-expert","title":"CLER: Cross-task Learning with Expert Representation to Generalize Reading and Understanding","date":"2019-11-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"tree-gated-deep-mixture-of-experts-for-pose","title":"Tree-gated Deep Mixture-of-Experts For Pose-robust Face Alignment","date":"2019-10-21","arxiv_id":"1910.09450","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-experts-variational-autoencoder-1","title":"Mixture-of-Experts Variational Autoencoder for clustering and generating from similarity-based representations","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moet-interpretable-and-verifiable-1","title":"MoET: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees","date":"2019-09-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-sparse-mixture-of-experts-for-visual","title":"Learning Sparse Mixture of Experts for Visual Question Answering","date":"2019-09-19","arxiv_id":"1909.09192","repositories_listed":0,"syntology":null},{"url":null,"slug":"recommending-what-video-to-watch-next-a","title":"Recommending what video to watch next: a multitask ranking system","date":"2019-09-10","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"rtm-stacking-results-for-machine-translation","title":"RTM Stacking Results for Machine Translation Performance Prediction","date":"2019-08-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"predicting-assisted-ventilation-in","title":"Predicting assisted ventilation in Amyotrophic Lateral Sclerosis using a mixture of experts and conformal predictors","date":"2019-07-30","arxiv_id":"1907.13070","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-in-gated-neural-networks","title":"Learning in Gated Neural Networks","date":"2019-06-06","arxiv_id":"1906.02777","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-learning-via-task-multi-clustering","title":"Multi-Task Learning via Task Multi-Clustering","date":"2019-05-16","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-parametric-and-nonparametric-models","title":"Combining Parametric and Nonparametric Models for Off-Policy Evaluation","date":"2019-05-14","arxiv_id":"1905.05787","repositories_listed":0,"syntology":null},{"url":null,"slug":"diverse-machine-translation-with-a-single","title":"Diverse Machine Translation with a Single Multinomial Latent Variable","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"plume-polyhedral-learning-using-mixture-of","title":"PLUME: Polyhedral Learning Using Mixture of Experts","date":"2019-04-22","arxiv_id":"1904.09948","repositories_listed":0,"syntology":null},{"url":null,"slug":"wenet-weighted-networks-for-recurrent-network","title":"WeNet: Weighted Networks for Recurrent Network Architecture Search","date":"2019-04-08","arxiv_id":"1904.03819","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-functional-equivalence-of-tsk-fuzzy","title":"On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression","date":"2019-03-25","arxiv_id":"1903.10572","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mixture-of-experts-model-for-predicting","title":"A mixture of experts model for predicting persistent weather patterns","date":"2019-03-24","arxiv_id":"1903.10012","repositories_listed":0,"syntology":null},{"url":null,"slug":"affect-in-tweets-using-experts-model","title":"Affect in Tweets Using Experts Model","date":"2019-03-20","arxiv_id":"1904.00762","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-routing-mixture-of-experts","title":"Hierarchical Routing Mixture of Experts","date":"2019-03-18","arxiv_id":"1903.07756","repositories_listed":0,"syntology":null},{"url":null,"slug":"uncertainty-aware-driver-trajectory","title":"Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections","date":"2019-01-16","arxiv_id":"1901.05105","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-sepsis-treatment-strategies-by","title":"Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning","date":"2019-01-15","arxiv_id":"1901.04670","repositories_listed":0,"syntology":null},{"url":null,"slug":"bayesian-shrinkage-in-mixture-of-experts","title":"Bayesian shrinkage in mixture of experts models: Identifying robust determinants of class membership","date":"2019-01-12","arxiv_id":"1809.04853","repositories_listed":0,"syntology":null},{"url":null,"slug":"dropout-regularization-in-hierarchical","title":"Dropout Regularization in Hierarchical Mixture of Experts","date":"2018-12-25","arxiv_id":"1812.10158","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-regression-experts-in-fmri","title":"Mixture of Regression Experts in fMRI Encoding","date":"2018-11-26","arxiv_id":"1811.10740","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-compose-topic-aware-mixture-of","title":"Learning to Compose Topic-Aware Mixture of Experts for Zero-Shot Video Captioning","date":"2018-11-07","arxiv_id":"1811.02765","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-mixture-of-expert-approach-for-low-cost","title":"A Mixture of Expert Approach for Low-Cost Customization of Deep Neural Networks","date":"2018-10-31","arxiv_id":"1811.00056","repositories_listed":0,"syntology":null},{"url":null,"slug":"regularized-maximum-likelihood-estimation-and","title":"Regularized Maximum Likelihood Estimation and Feature Selection in Mixtures-of-Experts Models","date":"2018-10-29","arxiv_id":"1810.12161","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-resource-multilingual-model-transfer-1","title":"Zero-Resource Multilingual Model Transfer: Learning What to Share","date":"2018-09-27","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"moe-spnet-a-mixture-of-experts-scene-parsing","title":"MoE-SPNet: A Mixture-of-Experts Scene Parsing Network","date":"2018-06-19","arxiv_id":"1806.07049","repositories_listed":0,"syntology":null},{"url":null,"slug":"modularity-matters-learning-invariant","title":"Modularity Matters: Learning Invariant Relational Reasoning Tasks","date":"2018-06-18","arxiv_id":"1806.06765","repositories_listed":0,"syntology":null},{"url":null,"slug":"megan-mixture-of-experts-of-generative","title":"MEGAN: Mixture of Experts of Generative Adversarial Networks for Multimodal Image Generation","date":"2018-05-07","arxiv_id":"1805.02481","repositories_listed":0,"syntology":null},{"url":null,"slug":"stylistic-variation-in-social-media-part-of","title":"Stylistic Variation in Social Media Part-of-Speech Tagging","date":"2018-04-19","arxiv_id":"1804.07331","repositories_listed":0,"syntology":null},{"url":null,"slug":"breaking-the-gridlock-in-mixture-of-experts","title":"Breaking the gridlock in Mixture-of-Experts: Consistent and Efficient Algorithms","date":"2018-02-21","arxiv_id":"1802.07417","repositories_listed":0,"syntology":null},{"url":null,"slug":"topic-compositional-neural-language-model","title":"Topic Compositional Neural Language Model","date":"2017-12-28","arxiv_id":"1712.09783","repositories_listed":0,"syntology":null},{"url":null,"slug":"diversity-promoting-bayesian-learning-of","title":"Diversity-Promoting Bayesian Learning of Latent Variable Models","date":"2017-11-23","arxiv_id":"1711.08770","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-gaussian-covariance-network","title":"Deep Gaussian Covariance Network","date":"2017-10-17","arxiv_id":"1710.06202","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-introduction-to-the-practical-and","title":"An Introduction to the Practical and Theoretical Aspects of Mixture-of-Experts Modeling","date":"2017-07-12","arxiv_id":"1707.03538","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-scale-youtube-8m-video-understanding","title":"Large-Scale YouTube-8M Video Understanding with Deep Neural Networks","date":"2017-06-14","arxiv_id":"1706.04488","repositories_listed":0,"syntology":null},{"url":null,"slug":"hard-mixtures-of-experts-for-large-scale","title":"Hard Mixtures of Experts for Large Scale Weakly Supervised Vision","date":"2017-04-20","arxiv_id":"1704.06363","repositories_listed":0,"syntology":null},{"url":null,"slug":"quality-resilient-deep-neural-networks","title":"Quality Resilient Deep Neural Networks","date":"2017-03-23","arxiv_id":"1703.08119","repositories_listed":0,"syntology":null},{"url":null,"slug":"changing-model-behavior-at-test-time-using","title":"Changing Model Behavior at Test-Time Using Reinforcement Learning","date":"2017-02-24","arxiv_id":"1702.07780","repositories_listed":0,"syntology":null},{"url":null,"slug":"visual-saliency-prediction-using-a-mixture-of","title":"Visual Saliency Prediction Using a Mixture of Deep Neural Networks","date":"2017-02-01","arxiv_id":"1702.00372","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-mixture-of-experts-modeling-using-the","title":"Robust mixture of experts modeling using the skew $t$ distribution","date":"2016-12-09","arxiv_id":"1612.06879","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-mixture-of-experts-modeling-using-the-1","title":"Robust mixture of experts modeling using the $t$ distribution","date":"2016-12-09","arxiv_id":"1701.07429","repositories_listed":0,"syntology":null},{"url":null,"slug":"lstm-based-mixture-of-experts-for-knowledge","title":"LSTM-based Mixture-of-Experts for Knowledge-Aware Dialogues","date":"2016-05-05","arxiv_id":"1605.01652","repositories_listed":0,"syntology":null}],"record_sha256":"495ebce8bd5adbc354c97a0e1e968c0fec12c07f5c4bc480f84babb39d30c250","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}