{"total":19,"rows":[{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72,"area":null},{"id":"2311.18823","title":"Initializing Models with Larger Ones","created":"2023-11-30","cited_by_count":39,"area":null},{"id":"2304.14535","title":"Deep Transfer Learning for Automatic Speech Recognition: Towards Better Generalization","created":"2023-04-27","cited_by_count":28,"area":null},{"id":"2402.05913","title":"Efficient Stagewise Pretraining via Progressive Subnetworks","created":"2024-02-08","cited_by_count":10,"area":null},{"id":"2311.05589","title":"A Coefficient Makes SVRG Effective","created":"2023-11-09","cited_by_count":7,"area":null},{"id":"2405.14159","title":"Super Tiny Language Models","created":"2024-05-23","cited_by_count":7,"area":null},{"id":"2504.14783","title":"How Effective Can Dropout Be in Multiple Instance Learning ?","created":"2025-04-21","cited_by_count":7,"area":null},{"id":"2401.10359","title":"Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting","created":"2024-01-18","cited_by_count":6,"area":null},{"id":"2505.24313","title":"Weak-to-Strong Generalization via Bregman Bias-Variance Decomposition","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2403.00946","title":"Fine-tuning with Very Large Dropout","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2404.06773","title":"Adapting LLaMA Decoder to Vision Transformer","created":"2024-04-10","cited_by_count":3,"area":null},{"id":"2510.07554","title":"Phase Diagram of Dropout for Two-Layer Neural Networks in the Mean-Field Regime","created":"2025-10-08","cited_by_count":3,"area":null},{"id":"2308.02287","title":"Frustratingly Easy Model Generalization by Dummy Risk Minimization","created":"2023-08-04","cited_by_count":2,"area":null},{"id":"2402.19002","title":"GoalNet: Goal Areas Oriented Pedestrian Trajectory Prediction","created":"2024-02-29","cited_by_count":1,"area":null},{"id":"2304.00040","title":"A robust deep learning-based damage identification approach for SHM considering missing data","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2307.08013","title":"Revisiting Implicit Models: Sparsity Trade-offs Capability in Weight-tied Model for Vision Tasks","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2408.05391","title":"SAMSA: Efficient Transformer for Many Data Modalities","created":"2024-08-10","cited_by_count":0,"area":null},{"id":"2410.07531","title":"Reducing the Cost of Dropout in Flash-Attention by Hiding RNG with GEMM","created":"2024-10-10","cited_by_count":0,"area":null},{"id":"2607.16761","title":"Dropout and Random Gradient Masking Are Asymptotically Equivalent in Large ResNets","created":"2026-07-18","cited_by_count":0,"area":null}],"next_cursor":null}