{"total":36,"rows":[{"id":"2302.10198","title":"Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT","created":"2023-02-19","cited_by_count":155,"area":null},{"id":"2406.04836","title":"Revisiting Catastrophic Forgetting in Large Language Model Tuning","created":"2024-06-07","cited_by_count":99,"area":null},{"id":"2304.11823","title":"Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization","created":"2023-04-24","cited_by_count":64,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2302.10429","title":"FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy","created":"2023-02-21","cited_by_count":49,"area":null},{"id":"2305.11584","title":"Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape","created":"2023-05-19","cited_by_count":46,"area":null},{"id":"2302.04083","title":"Improving the Model Consistency of Decentralized Federated Learning","created":"2023-02-08","cited_by_count":45,"area":null},{"id":"2404.00986","title":"Make Continual Learning Stronger via C-Flat","created":"2024-04-01","cited_by_count":35,"area":null},{"id":"2303.11242","title":"Make Landscape Flatter in Differentially Private Federated Learning","created":"2023-03-20","cited_by_count":33,"area":null},{"id":"2303.13087","title":"Robust Generalization against Photon-Limited Corruptions via Worst-Case Sharpness Minimization","created":"2023-03-23","cited_by_count":29,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2305.15287","title":"The Crucial Role of Normalization in Sharpness-Aware Minimization","created":"2023-05-24","cited_by_count":26,"area":null},{"id":"2212.01853","title":"Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE","created":"2022-12-04","cited_by_count":24,"area":null},{"id":"2303.00565","title":"AdaSAM: Boosting Sharpness-Aware Minimization with Adaptive Learning Rate and Momentum for Training Deep Neural Networks","created":"2023-03-01","cited_by_count":21,"area":null},{"id":"2305.05392","title":"Sharpness-Aware Minimization Alone can Improve Adversarial Robustness","created":"2023-05-09","cited_by_count":14,"area":null},{"id":"2406.03682","title":"A Universal Class of Sharpness-Aware Minimization Algorithms","created":"2024-06-06","cited_by_count":14,"area":null},{"id":"2302.09268","title":"Bag of Tricks for Effective Language Model Pretraining and Downstream Adaptation: A Case Study on GLUE","created":"2023-02-18","cited_by_count":11,"area":null},{"id":"2501.01045","title":"ZeroFlow: Overcoming Catastrophic Forgetting is Easier than You Think","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2305.15157","title":"Towards More Suitable Personalization in Federated Learning via Decentralized Partial Model Training","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2305.15275","title":"Self-Evolution Learning for Discriminative Language Model Pretraining","created":"2023-05-24","cited_by_count":8,"area":null},{"id":"2410.10683","title":"SAMPa: Sharpness-aware Minimization Parallelized","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2308.08290","title":"DFedADMM: Dual Constraints Controlled Model Inconsistency for Decentralized Federated Learning","created":"2023-08-16","cited_by_count":6,"area":null},{"id":"2305.00873","title":"Towards the Flatter Landscape and Better Generalization in Federated Learning under Client-level Differential Privacy","created":"2023-05-01","cited_by_count":5,"area":null},{"id":"2310.05093","title":"Asymmetrically Decentralized Federated Learning","created":"2023-10-08","cited_by_count":5,"area":null},{"id":"2502.19571","title":"LORENZA: Enhancing Generalization in Low-Rank Gradient LLM Training via Efficient Zeroth-Order Adaptive SAM","created":"2025-02-26","cited_by_count":5,"area":null},{"id":"2304.10354","title":"Prompt-Learning for Cross-Lingual Relation Extraction","created":"2023-04-20","cited_by_count":4,"area":null},{"id":"2407.12993","title":"Improving SAM Requires Rethinking its Optimization Formulation","created":"2024-07-17","cited_by_count":4,"area":null},{"id":"2602.07145","title":"Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2310.13315","title":"Zero-Shot Sharpness-Aware Quantization for Pre-trained Language Models","created":"2023-10-20","cited_by_count":2,"area":null},{"id":"2312.02820","title":"Clustering Pseudo Language Family in Multilingual Translation Models with Fisher Information Matrix","created":"2023-12-05","cited_by_count":2,"area":null},{"id":"2510.24919","title":"Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2508.18860","title":"C-Flat++: Towards a More Efficient and Powerful Framework for Continual Learning","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2602.09395","title":"Sparse Layer Sharpness-Aware Minimization for Efficient Fine-Tuning","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2604.11064","title":"A Faster Path to Continual Learning","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2509.21818","title":"Sharpness-Aware Minimization Can Hallucinate Minimizers","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2607.18306","title":"Gradient-Energy Guided Block-Wise Perturbations for Sharpness-Aware Minimization","created":"2026-07-17","cited_by_count":0,"area":null}],"next_cursor":null}