{"total":13,"rows":[{"id":"2210.00094","title":"Improving Robustness with Adaptive Weight Decay","created":"2022-09-30","cited_by_count":13,"area":null},{"id":"2506.14562","title":"AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs","created":"2025-06-17","cited_by_count":13,"area":null},{"id":"2202.08978","title":"Cyclical Focal Loss","created":"2022-02-16","cited_by_count":8,"area":null},{"id":"2503.15111","title":"FedLWS: Federated Learning with Adaptive Layer-wise Weight Shrinking","created":"2025-03-19","cited_by_count":7,"area":null},{"id":"2504.17160","title":"OUI Need to Talk About Weight Decay: A New Perspective on Overfitting Detection","created":"2025-04-24","cited_by_count":7,"area":null},{"id":"2202.08835","title":"General Cyclical Training of Neural Networks","created":"2022-02-17","cited_by_count":5,"area":null},{"id":"2311.09058","title":"Improving Deep Learning Optimization through Constrained Parameter Regularization","created":"2023-11-15","cited_by_count":5,"area":null},{"id":"2102.03018","title":"Evaluating Deep Learning in SystemML using Layer-wise Adaptive Rate Scaling(LARS) Optimizer","created":"2021-02-05","cited_by_count":1,"area":null},{"id":"2604.27063","title":"Learning to Forget: Continual Learning with Adaptive Weight Decay","created":"2026-04-29","cited_by_count":1,"area":null},{"id":"2311.12356","title":"Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2404.10454","title":"A Computer Vision-Based Quality Assessment Technique for the automatic control of consumables for analytical laboratories","created":"2024-04-16","cited_by_count":0,"area":null},{"id":"2605.10161","title":"OUIDecay: Adaptive Layer-wise Weight Decay for CNNs Using Online Activation Patterns","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2609.05730","title":"Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance","created":"2026-09-04","cited_by_count":0,"area":null}],"next_cursor":null}