{"list":"other","total":53,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2010.01412","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","created":"2020-10-03","cited_by_count":1417},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1803.05407","title":"Averaging Weights Leads to Wider Optima and Better Generalization","created":"2018-03-14","cited_by_count":1209},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"1911.04933","title":"Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks","created":"2019-11-12","cited_by_count":618},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2002.08484","title":"Estimating Training Data Influence by Tracing Gradient Descent","created":"2020-02-19","cited_by_count":580},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"1611.01838","title":"Entropy-SGD: Biasing Gradient Descent Into Wide Valleys","created":"2016-11-06","cited_by_count":359},{"id":"2102.11600","title":"ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks","created":"2021-02-23","cited_by_count":293},{"id":"2303.14186","title":"TRAK: Attributing Model Behavior at Scale","created":"2023-03-24","cited_by_count":283},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260},{"id":"2006.14651","title":"Influence Functions in Deep Learning Are Fragile","created":"2020-06-25","cited_by_count":252},{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202},{"id":"1705.10941","title":"Spectral Norm Regularization for Improving the Generalizability of Deep Learning","created":"2017-05-31","cited_by_count":182},{"id":"2110.14049","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","created":"2021-10-26","cited_by_count":165},{"id":"2012.13431","title":"Mixed-Privacy Forgetting in Deep Networks","created":"2020-12-24","cited_by_count":163},{"id":"2206.06232","title":"Towards Understanding Sharpness-Aware Minimization","created":"2022-06-13","cited_by_count":146},{"id":"2005.06676","title":"Explaining Black Box Predictions and Unveiling Data Artifacts through Influence Functions","created":"2020-05-14","cited_by_count":144},{"id":"2206.02618","title":"Generalized Federated Learning via Sharpness Aware Minimization","created":"2022-06-06","cited_by_count":144},{"id":"2110.03141","title":"Efficient Sharpness-aware Minimization for Improved Training of Neural Networks","created":"2021-10-07","cited_by_count":137},{"id":"2203.02714","title":"Towards Efficient and Scalable Sharpness-Aware Minimization","created":"2022-03-05","cited_by_count":129},{"id":"2202.03599","title":"Penalizing Gradient Norm for Efficiently Improving Generalization in Deep Learning","created":"2022-02-08","cited_by_count":122},{"id":"1909.11671","title":"Data Valuation using Reinforcement Learning","created":"2019-09-25","cited_by_count":116},{"id":"2110.08529","title":"Sharpness-Aware Minimization Improves Language Model Generalization","created":"2021-10-16","cited_by_count":108},{"id":"1810.03611","title":"Understanding the Origins of Bias in Word Embeddings","created":"2018-10-08","cited_by_count":91},{"id":"1901.10501","title":"Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions","created":"2019-01-29","cited_by_count":48},{"id":"2305.16292","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","created":"2023-05-25","cited_by_count":38},{"id":"2305.16971","title":"Theoretical and Practical Perspectives on what Influence Functions Do","created":"2023-05-26","cited_by_count":29},{"id":"2312.10336","title":"Certified Minimax Unlearning with Generalization Rates and Deletion Capacity","created":"2023-12-16","cited_by_count":29},{"id":"2405.15476","title":"Editable Concept Bottleneck Models","created":"2024-05-24","cited_by_count":23},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20},{"id":"2304.09762","title":"Practical Differentially Private and Byzantine-resilient Federated Learning","created":"2023-04-15","cited_by_count":18},{"id":"2007.09081","title":"Multi-Stage Influence Function","created":"2020-07-17","cited_by_count":16},{"id":"2502.04204","title":"Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence","created":"2025-02-06","cited_by_count":14},{"id":"2502.17515","title":"Towards User-level Private Reinforcement Learning with Human Feedback","created":"2025-02-22","cited_by_count":14},{"id":"2311.06888","title":"Preserving Node-level Privacy in Graph Neural Networks","created":"2023-11-12","cited_by_count":11},{"id":"2502.09022","title":"Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning","created":"2025-02-13","cited_by_count":11},{"id":"1910.00482","title":"Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data","created":"2019-10-01","cited_by_count":9},{"id":"2310.06112","title":"Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach","created":"2023-10-09","cited_by_count":9},{"id":"2402.11989","title":"Privacy-Preserving Low-Rank Adaptation against Membership Inference Attacks for Latent Diffusion Models","created":"2024-02-19","cited_by_count":9},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8},{"id":"2503.18317","title":"Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization","created":"2025-03-24","cited_by_count":5},{"id":"2501.15963","title":"Evaluating Data Influence in Meta Learning","created":"2025-01-27","cited_by_count":4},{"id":"2408.10468","title":"Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions","created":"2024-08-20","cited_by_count":2}],"next_cursor":null}