{"total":21,"rows":[{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283,"area":null},{"id":"2305.12827","title":"Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models","created":"2023-05-22","cited_by_count":221,"area":null},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121,"area":null},{"id":"2203.11481","title":"Mixed Differential Privacy in Computer Vision","created":"2022-03-22","cited_by_count":54,"area":null},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47,"area":null},{"id":"2207.06343","title":"TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels","created":"2022-07-13","cited_by_count":26,"area":null},{"id":"2307.08114","title":"Tangent Model Composition for Ensembling and Continual Fine-tuning","created":"2023-07-16","cited_by_count":25,"area":null},{"id":"2305.18449","title":"Taming AI Bots: Controllability of Neural States in Large Language Models","created":"2023-05-29","cited_by_count":22,"area":null},{"id":"2207.09413","title":"SphereFed: Hyperspherical Federated Learning","created":"2022-07-19","cited_by_count":19,"area":null},{"id":"2307.08122","title":"Tangent Transformers for Composition, Privacy and Removal","created":"2023-07-16","cited_by_count":13,"area":null},{"id":"2208.08112","title":"DLCFT: Deep Linear Continual Fine-Tuning for General Incremental Learning","created":"2022-08-17","cited_by_count":11,"area":null},{"id":"2209.15208","title":"Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel","created":"2022-09-30","cited_by_count":7,"area":null},{"id":"2303.14333","title":"Train/Test-Time Adaptation with Retrieval","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2111.09785","title":"DIVA: Dataset Derivative of a Learning Task","created":"2021-11-18","cited_by_count":5,"area":null},{"id":"2211.13108","title":"Integral Continual Learning Along the Tangent Vector Field of Tasks","created":"2022-11-23","cited_by_count":3,"area":null},{"id":"2602.17385","title":"Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature","created":"2026-02-19","cited_by_count":3,"area":null},{"id":"2203.16701","title":"Towards Differential Relational Privacy and its use in Question Answering","created":"2022-03-30","cited_by_count":1,"area":null},{"id":"2506.20025","title":"Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2106.13870","title":"Scene Uncertainty and the Wellington Posterior of Deterministic Image Classifiers","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2504.17963","title":"Mathematics of Continual Learning","created":"2025-04-24","cited_by_count":0,"area":null},{"id":"2511.19803","title":"Scalable Data Attribution via Forward-Only Test-Time Inference","created":"2025-11-25","cited_by_count":0,"area":null}],"next_cursor":null}