{"total":26,"rows":[{"id":"2205.09739","title":"Diverse Weight Averaging for Out-of-Distribution Generalization","created":"2022-05-19","cited_by_count":148,"area":null},{"id":"2211.08403","title":"REPAIR: REnormalizing Permuted Activations for Interpolation Repair","created":"2022-11-15","cited_by_count":120,"area":null},{"id":"2309.15698","title":"Deep Model Fusion: A Survey","created":"2023-09-27","cited_by_count":91,"area":null},{"id":"2202.00661","title":"When Do Flat Minima Optimizers Work?","created":"2022-02-01","cited_by_count":78,"area":null},{"id":"2209.14981","title":"Stop Wasting My Time! Saving Days of ImageNet and BERT Training with Latest Weight Averaging","created":"2022-09-29","cited_by_count":54,"area":null},{"id":"2402.09240","title":"Switch EMA: A Free Lunch for Better Flatness and Sharpness","created":"2024-02-14","cited_by_count":9,"area":null},{"id":"2511.21437","title":"A Systematic Study of In-the-Wild Model Merging for Large Language Models","created":"2025-11-26","cited_by_count":5,"area":null},{"id":"2306.00352","title":"Improving Energy Conserving Descent for Machine Learning: Theory and Practice","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2306.05772","title":"A Boosted Model Ensembling Approach to Ball Action Spotting in Videos: The Runner-Up Solution to CVPR'23 SoccerNet Challenge","created":"2023-06-09","cited_by_count":4,"area":null},{"id":"2303.12992","title":"A Survey of Historical Learning: Learning Models with Learning History","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2504.10231","title":"A Model Zoo of Vision Transformers","created":"2025-04-14","cited_by_count":3,"area":null},{"id":"2209.14742","title":"Learning Gradient-based Mixup with Extrapolation toward Flatter Minima for Domain Generalization","created":"2022-09-29","cited_by_count":2,"area":null},{"id":"2306.09121","title":"The Split Matters: Flat Minima Methods for Improving the Performance of GNNs","created":"2023-06-15","cited_by_count":2,"area":null},{"id":"2401.02465","title":"Interpretable Time Series Models for Wastewater Modeling in Combined Sewer Overflows","created":"2024-01-04","cited_by_count":2,"area":null},{"id":"2407.00356","title":"Enhancing Accuracy and Parameter-Efficiency of Neural Representations for Network Parameterization","created":"2024-06-29","cited_by_count":2,"area":null},{"id":"2604.02719","title":"MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2202.06658","title":"PFGE: Parsimonious Fast Geometric Ensembling of DNNs","created":"2022-02-14","cited_by_count":1,"area":null},{"id":"2207.11211","title":"Improving Predictive Performance and Calibration by Weight Fusion in Semantic Segmentation","created":"2022-07-22","cited_by_count":1,"area":null},{"id":"2209.12581","title":"Two-Tailed Averaging: Anytime, Adaptive, Once-in-a-While Optimal Weight Averaging for Better Generalization","created":"2022-09-26","cited_by_count":1,"area":null},{"id":"2503.14396","title":"Aggregation on Learnable Manifolds for Asynchronous Federated Optimization","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2505.22085","title":"PADAM: Parallel averaged Adam reduces the error for stochastic optimization in scientific machine learning","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2509.05142","title":"Foundational Models and Federated Learning: Survey, Taxonomy, Challenges and Practical Insights","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2310.11094","title":"Relearning Forgotten Knowledge: on Forgetting, Overfit and Training-Free Ensembles of DNNs","created":"2023-10-17","cited_by_count":0,"area":null},{"id":"2507.08686","title":"Forget Me Not: Fighting Local Overfitting with Knowledge Fusion and Distillation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2602.19332","title":"Training-Free Cross-Architecture Merging for Graph Neural Networks","created":"2026-02-22","cited_by_count":0,"area":null},{"id":"2608.14373","title":"Boosting Data Augmentation with Stochastic Weight Averaging","created":"2026-08-14","cited_by_count":0,"area":null}],"next_cursor":null}