{"total":13,"rows":[{"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":"2510.12402","title":"Cautious Weight Decay","created":"2025-10-14","cited_by_count":13,"area":null},{"id":"2412.11768","title":"No More Adam: Learning Rate Scaling at Initialization is All You Need","created":"2024-12-16","cited_by_count":8,"area":null},{"id":"2303.09044","title":"CoLo-CAM: Class Activation Mapping for Object Co-Localization in Weakly-Labeled Unconstrained Videos","created":"2023-03-16","cited_by_count":7,"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":"2311.09058","title":"Improving Deep Learning Optimization through Constrained Parameter Regularization","created":"2023-11-15","cited_by_count":5,"area":null},{"id":"2410.12607","title":"Low-Rank Adversarial PGD Attack","created":"2024-10-16","cited_by_count":4,"area":null},{"id":"2507.04683","title":"Recovering Plasticity of Neural Networks via Soft Weight Rescaling","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2511.09775","title":"Privacy-Preserving Explainable AIoT Application via SHAP Entropy Regularization","created":"2025-11-12","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":"2604.22838","title":"Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning","created":"2026-04-21","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}