{"total":24,"rows":[{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94,"area":null},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87,"area":null},{"id":"2302.05185","title":"On Penalty-based Bilevel Gradient Descent Method","created":"2023-02-10","cited_by_count":87,"area":null},{"id":"2312.04528","title":"Using Large Language Models for Hyperparameter Optimization","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46,"area":null},{"id":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20,"area":null},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19,"area":null},{"id":"2401.15863","title":"Importance-Aware Adaptive Dataset Distillation","created":"2024-01-29","cited_by_count":18,"area":null},{"id":"2406.04284","title":"What is Dataset Distillation Learning?","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2301.13501","title":"Auxiliary Learning as an Asymmetric Bargaining Game","created":"2023-01-31","cited_by_count":12,"area":null},{"id":"2507.14740","title":"Better Training Data Attribution via Better Inverse Hessian-Vector Products","created":"2025-07-19","cited_by_count":10,"area":null},{"id":"2302.09726","title":"Nystrom Method for Accurate and Scalable Implicit Differentiation","created":"2023-02-20","cited_by_count":8,"area":null},{"id":"2304.11153","title":"Low-Variance Gradient Estimation in Unrolled Computation Graphs with ES-Single","created":"2023-04-21","cited_by_count":7,"area":null},{"id":"2408.13237","title":"JacNet: Learning Functions with Structured Jacobians","created":"2024-08-23","cited_by_count":7,"area":null},{"id":"2411.11329","title":"Color-Oriented Redundancy Reduction in Dataset Distillation","created":"2024-11-18","cited_by_count":6,"area":null},{"id":"2306.02422","title":"A Generalized Alternating Method for Bilevel Learning under the Polyak-{\\L}ojasiewicz Condition","created":"2023-06-04","cited_by_count":5,"area":null},{"id":"2406.18630","title":"Improving Hyperparameter Optimization with Checkpointed Model Weights","created":"2024-06-26","cited_by_count":5,"area":null},{"id":"2601.08828","title":"Motion Attribution for Video Generation","created":"2026-01-13","cited_by_count":5,"area":null},{"id":"2302.09731","title":"CMVAE: Causal Meta VAE for Unsupervised Meta-Learning","created":"2023-02-20","cited_by_count":3,"area":null},{"id":"2305.15042","title":"Test like you Train in Implicit Deep Learning","created":"2023-05-24","cited_by_count":3,"area":null},{"id":"2410.10417","title":"A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2505.22509","title":"Accelerating Optimization via Differentiable Stopping Time","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2310.17386","title":"A Challenge in Reweighting Data with Bilevel Optimization","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2605.07577","title":"Bilevel Graph Structure Learning, Revisited: Inner-Channel Origins of the Reported Gain","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}