{"total":21,"rows":[{"id":"2302.06600","title":"Task-Specific Skill Localization in Fine-tuned Language Models","created":"2023-02-13","cited_by_count":105,"area":null},{"id":"2407.07972","title":"Deconstructing What Makes a Good Optimizer for Language Models","created":"2024-07-10","cited_by_count":41,"area":null},{"id":"2309.00079","title":"On the Implicit Bias of Adam","created":"2023-08-31","cited_by_count":27,"area":null},{"id":"2302.11861","title":"Out-of-Domain Robustness via Targeted Augmentations","created":"2023-02-23","cited_by_count":24,"area":null},{"id":"2307.01189","title":"Trainable Transformer in Transformer","created":"2023-07-03","cited_by_count":17,"area":null},{"id":"2506.12543","title":"Is your batch size the problem? Revisiting the Adam-SGD gap in language modeling","created":"2025-06-14","cited_by_count":15,"area":null},{"id":"2212.04486","title":"A New Linear Scaling Rule for Private Adaptive Hyperparameter Optimization","created":"2022-12-08","cited_by_count":11,"area":null},{"id":"2305.19402","title":"Contextual Vision Transformers for Robust Representation Learning","created":"2023-05-30","cited_by_count":10,"area":null},{"id":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2403.12229","title":"Fusion Transformer with Object Mask Guidance for Image Forgery Analysis","created":"2024-03-18","cited_by_count":7,"area":null},{"id":"2303.02241","title":"Domain adaptation using optimal transport for invariant learning using histopathology datasets","created":"2023-03-03","cited_by_count":4,"area":null},{"id":"2312.10282","title":"RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification","created":"2023-12-16","cited_by_count":3,"area":null},{"id":"2401.10220","title":"AutoFT: Learning an Objective for Robust Fine-Tuning","created":"2024-01-18","cited_by_count":3,"area":null},{"id":"2404.06277","title":"Learning Embeddings with Centroid Triplet Loss for Object Identification in Robotic Grasping","created":"2024-04-09","cited_by_count":3,"area":null},{"id":"2401.10962","title":"One Step Learning, One Step Review","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2411.14860","title":"Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems","created":"2024-11-22","cited_by_count":1,"area":null},{"id":"2606.14259","title":"Beyond a Single Explanation of the Adam--SGD Gap","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2301.06133","title":"Improving Reliability of Fine-tuning with Block-wise Optimisation","created":"2023-01-15","cited_by_count":0,"area":null},{"id":"2312.06121","title":"Can LLMs Configure Software Tools","created":"2023-12-11","cited_by_count":0,"area":null},{"id":"2511.22001","title":"When Do Domain-Specific Foundation Models Justify Their Cost? A Systematic Evaluation Across Retinal Imaging Tasks","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2608.13660","title":"What to Preserve, Where to Adapt: A Depth-Wise Analysis of Forgetting in Continual Gynecological Image Segmentation","created":"2026-08-13","cited_by_count":0,"area":null}],"next_cursor":null}