{"total":37,"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":"2104.08247","title":"What to Pre-Train on? Efficient Intermediate Task Selection","created":"2021-04-16","cited_by_count":63,"area":null},{"id":"2106.06770","title":"What can linearized neural networks actually say about generalization?","created":"2021-06-12","cited_by_count":49,"area":null},{"id":"2106.09362","title":"Frustratingly Easy Transferability Estimation","created":"2021-06-17","cited_by_count":45,"area":null},{"id":"2111.06977","title":"Scalable Diverse Model Selection for Accessible Transfer Learning","created":"2021-11-12","cited_by_count":40,"area":null},{"id":"2402.02314","title":"Selecting Large Language Model to Fine-tune via Rectified Scaling Law","created":"2024-02-04","cited_by_count":33,"area":null},{"id":"2110.08611","title":"Deep Active Learning by Leveraging Training Dynamics","created":"2021-10-16","cited_by_count":32,"area":null},{"id":"2306.03900","title":"Model Spider: Learning to Rank Pre-Trained Models Efficiently","created":"2023-06-06","cited_by_count":32,"area":null},{"id":"2502.17282","title":"Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing","created":"2025-02-24","cited_by_count":25,"area":null},{"id":"2203.14577","title":"Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?","created":"2022-03-28","cited_by_count":18,"area":null},{"id":"2302.13602","title":"The Role of Pre-training Data in Transfer Learning","created":"2023-02-27","cited_by_count":17,"area":null},{"id":"2110.06893","title":"Newer is not always better: Rethinking transferability metrics, their peculiarities, stability and performance","created":"2021-10-13","cited_by_count":16,"area":null},{"id":"2402.15231","title":"Which Model to Transfer? A Survey on Transferability Estimation","created":"2024-02-23","cited_by_count":13,"area":null},{"id":"2303.14333","title":"Train/Test-Time Adaptation with Retrieval","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2406.07337","title":"Transferring Knowledge from Large Foundation Models to Small Downstream Models","created":"2024-06-11","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":"2311.04592","title":"On Characterizing the Evolution of Embedding Space of Neural Networks using Algebraic Topology","created":"2023-11-08","cited_by_count":5,"area":null},{"id":"2312.00656","title":"Simple Transferability Estimation for Regression Tasks","created":"2023-12-01","cited_by_count":5,"area":null},{"id":"2404.03988","title":"Model Selection with Model Zoo via Graph Learning","created":"2024-04-05","cited_by_count":5,"area":null},{"id":"2503.22984","title":"Optimal Transport-Guided Source-Free Adaptation for Face Anti-Spoofing","created":"2025-03-29","cited_by_count":5,"area":null},{"id":"2510.17299","title":"Exploring Structural Degradation in Dense Representations for Self-supervised Learning","created":"2025-10-20","cited_by_count":5,"area":null},{"id":"2204.01457","title":"SHiFT: An Efficient, Flexible Search Engine for Transfer Learning","created":"2022-04-04","cited_by_count":3,"area":null},{"id":"2206.11173","title":"Cold Posteriors through PAC-Bayes","created":"2022-06-22","cited_by_count":3,"area":null},{"id":"2303.04105","title":"Your representations are in the network: composable and parallel adaptation for large scale models","created":"2023-03-07","cited_by_count":3,"area":null},{"id":"2509.04208","title":"One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo","created":"2025-09-04","cited_by_count":3,"area":null},{"id":"2509.23592","title":"Toward a Holistic Approach to Continual Model Merging","created":"2025-09-28","cited_by_count":3,"area":null},{"id":"2307.05741","title":"Towards Robust and Efficient Continual Language Learning","created":"2023-07-11","cited_by_count":2,"area":null},{"id":"2412.16251","title":"Know2Vec: A Black-Box Proxy for Neural Network Retrieval","created":"2024-12-20","cited_by_count":2,"area":null},{"id":"2509.23695","title":"Estimating Time Series Foundation Model Transferability via In-Context Learning","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2602.08239","title":"Linearization Explains Fine-Tuning in Large Language Models","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2107.00191","title":"Unsupervised Model Drift Estimation with Batch Normalization Statistics for Dataset Shift Detection and Model Selection","created":"2021-07-01","cited_by_count":1,"area":null},{"id":"2202.01958","title":"Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning","created":"2022-02-04","cited_by_count":1,"area":null},{"id":"2503.18528","title":"k-NN as a Simple and Effective Estimator of Transferability","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2605.07075","title":"ModelLens: Finding the Best for Your Task from Myriads of Models","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2306.15918","title":"On information captured by neural networks: connections with memorization and generalization","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2307.02693","title":"Kernels, Data & Physics","created":"2023-07-05","cited_by_count":0,"area":null}],"next_cursor":null}