{"total":23,"rows":[{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2202.06985","title":"Deep Ensembles Work, But Are They Necessary?","created":"2022-02-14","cited_by_count":63,"area":null},{"id":"2210.09184","title":"Packed-Ensembles for Efficient Uncertainty Estimation","created":"2022-10-17","cited_by_count":49,"area":null},{"id":"2209.05310","title":"On the Factory Floor: ML Engineering for Industrial-Scale Ads Recommendation Models","created":"2022-09-12","cited_by_count":34,"area":null},{"id":"2103.06132","title":"MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks","created":"2021-03-10","cited_by_count":32,"area":null},{"id":"2509.14786","title":"Pre-training under infinite compute","created":"2025-09-18","cited_by_count":29,"area":null},{"id":"2111.03577","title":"Mixtures of Laplace Approximations for Improved Post-Hoc Uncertainty in Deep Learning","created":"2021-11-05","cited_by_count":25,"area":null},{"id":"2302.00704","title":"Pathologies of Predictive Diversity in Deep Ensembles","created":"2023-02-01","cited_by_count":16,"area":null},{"id":"2407.05385","title":"Harmony in Diversity: Merging Neural Networks with Canonical Correlation Analysis","created":"2024-07-07","cited_by_count":9,"area":null},{"id":"2206.10566","title":"Ensembling over Classifiers: a Bias-Variance Perspective","created":"2022-06-21","cited_by_count":6,"area":null},{"id":"2106.04767","title":"Ex uno plures: Splitting One Model into an Ensemble of Subnetworks","created":"2021-06-09","cited_by_count":5,"area":null},{"id":"2310.02258","title":"A Neural Scaling Law from Lottery Ticket Ensembling","created":"2023-10-03","cited_by_count":5,"area":null},{"id":"2505.00985","title":"Position: Enough of Scaling LLMs! Lets Focus on Downscaling","created":"2025-05-02","cited_by_count":5,"area":null},{"id":"2601.16936","title":"Is BatchEnsemble a Single Model? On Calibration and Diversity of Efficient Ensembles","created":"2026-01-23","cited_by_count":4,"area":null},{"id":"2302.03364","title":"Population-size-Aware Policy Optimization for Mean-Field Games","created":"2023-02-07","cited_by_count":3,"area":null},{"id":"2202.06499","title":"Real World Large Scale Recommendation Systems Reproducibility and Smooth Activations","created":"2022-02-14","cited_by_count":2,"area":null},{"id":"2510.20690","title":"Neural Diversity Regularizes Hallucinations in Language Models","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2206.13491","title":"Effective training-time stacking for ensembling of deep neural networks","created":"2022-06-27","cited_by_count":1,"area":null},{"id":"2402.14184","title":"Beyond Simple Averaging: Improving NLP Ensemble Performance with Topological-Data-Analysis-Based Weighting","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2511.04514","title":"Linear Mode Connectivity under Data Shifts for Deep Ensembles of Image Classifiers","created":"2025-11-06","cited_by_count":1,"area":null},{"id":"2205.14761","title":"Modeling Disagreement in Automatic Data Labelling for Semi-Supervised Learning in Clinical Natural Language Processing","created":"2022-05-29","cited_by_count":0,"area":null},{"id":"2412.15467","title":"Non-Uniform Parameter-Wise Model Merging","created":"2024-12-20","cited_by_count":0,"area":null},{"id":"2607.05025","title":"Uncertainty-aware damage identification in short-span bridges via physics-informed variational autoencoder","created":"2026-07-06","cited_by_count":0,"area":null}],"next_cursor":null}