{"total":64,"rows":[{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532,"area":null},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399,"area":null},{"id":"2302.03169","title":"Data Selection for Language Models via Importance Resampling","created":"2023-02-06","cited_by_count":329,"area":null},{"id":"2103.00123","title":"GRAD-MATCH: Gradient Matching based Data Subset Selection for Efficient Deep Model Training","created":"2021-02-27","cited_by_count":274,"area":null},{"id":"2401.12926","title":"DsDm: Model-Aware Dataset Selection with Datamodels","created":"2024-01-23","cited_by_count":105,"area":null},{"id":"2107.00717","title":"SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios","created":"2021-07-01","cited_by_count":84,"area":null},{"id":"2504.13818","title":"Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning","created":"2025-04-18","cited_by_count":84,"area":"lr"},{"id":"2106.07760","title":"RETRIEVE: Coreset Selection for Efficient and Robust Semi-Supervised Learning","created":"2021-06-14","cited_by_count":74,"area":null},{"id":"2103.00128","title":"PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selection","created":"2021-02-27","cited_by_count":51,"area":null},{"id":"2202.00132","title":"Submodularity In Machine Learning and Artificial Intelligence","created":"2022-01-31","cited_by_count":38,"area":null},{"id":"2210.06640","title":"Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities","created":"2022-10-13","cited_by_count":38,"area":null},{"id":"2106.15324","title":"Effective Evaluation of Deep Active Learning on Image Classification Tasks","created":"2021-06-16","cited_by_count":37,"area":null},{"id":"2405.02774","title":"Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs","created":"2024-05-05","cited_by_count":32,"area":null},{"id":"2112.00166","title":"TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Information","created":"2021-11-30","cited_by_count":27,"area":null},{"id":"2203.08212","title":"AUTOMATA: Gradient Based Data Subset Selection for Compute-Efficient Hyper-parameter Tuning","created":"2022-03-15","cited_by_count":22,"area":null},{"id":"2103.03757","title":"Discrepancy-Based Active Learning for Domain Adaptation","created":"2021-03-05","cited_by_count":17,"area":null},{"id":"2403.08370","title":"SMART: Submodular Data Mixture Strategy for Instruction Tuning","created":"2024-03-13","cited_by_count":17,"area":null},{"id":"2505.19051","title":"Efficient Data Selection at Scale via Influence Distillation","created":"2025-05-25","cited_by_count":15,"area":null},{"id":"2106.12491","title":"Training Data Subset Selection for Regression with Controlled Generalization Error","created":"2021-06-23","cited_by_count":14,"area":null},{"id":"2303.05151","title":"Provable Data Subset Selection For Efficient Neural Network Training","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2302.12366","title":"Less is More: Data Pruning for Faster Adversarial Training","created":"2023-02-23","cited_by_count":13,"area":null},{"id":"2409.12255","title":"Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks","created":"2024-09-18","cited_by_count":13,"area":null},{"id":"2301.13287","title":"MILO: Model-Agnostic Subset Selection Framework for Efficient Model Training and Tuning","created":"2023-01-30","cited_by_count":9,"area":null},{"id":"2312.10602","title":"A Weighted K-Center Algorithm for Data Subset Selection","created":"2023-12-17","cited_by_count":9,"area":null},{"id":"2105.00043","title":"Submodular Mutual Information for Targeted Data Subset Selection","created":"2021-04-30","cited_by_count":8,"area":null},{"id":"2201.04768","title":"On Sampling Collaborative Filtering Datasets","created":"2022-01-13","cited_by_count":8,"area":null},{"id":"2202.10680","title":"Submodlib: A Submodular Optimization Library","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2310.00165","title":"SCoRe: Submodular Combinatorial Representation Learning","created":"2023-09-29","cited_by_count":7,"area":null},{"id":"2410.16710","title":"Influential Language Data Selection via Gradient Trajectory Pursuit","created":"2024-10-22","cited_by_count":7,"area":null},{"id":"2511.10721","title":"Fast Data Attribution for Text-to-Image Models","created":"2025-11-13","cited_by_count":7,"area":"diffusion"},{"id":"2106.10836","title":"Active Learning for Deep Neural Networks on Edge Devices","created":"2021-06-21","cited_by_count":6,"area":null},{"id":"2310.16499","title":"Data Optimization in Deep Learning: A Survey","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2401.06989","title":"Gradient Coreset for Federated Learning","created":"2024-01-13","cited_by_count":6,"area":null},{"id":"2104.12835","title":"Less is more: Selecting informative and diverse subsets with balancing constraints","created":"2021-04-26","cited_by_count":5,"area":null},{"id":"2210.11717","title":"A Survey of Dataset Refinement for Problems in Computer Vision Datasets","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2307.07328","title":"Boosting Backdoor Attack with A Learnable Poisoning Sample Selection Strategy","created":"2023-07-14","cited_by_count":5,"area":null},{"id":"2504.20644","title":"Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection","created":"2025-04-29","cited_by_count":5,"area":null},{"id":"2301.12052","title":"Leveraging Importance Weights in Subset Selection","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2502.18955","title":"Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset","created":"2025-02-26","cited_by_count":4,"area":"offlinerl"},{"id":"2510.00303","title":"Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection","created":"2025-09-30","cited_by_count":4,"area":null},{"id":"2201.12928","title":"PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information","created":"2022-01-30","cited_by_count":3,"area":null},{"id":"2211.11546","title":"PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2310.09983","title":"Farzi Data: Autoregressive Data Distillation","created":"2023-10-15","cited_by_count":3,"area":null},{"id":"2205.10403","title":"Tackling Provably Hard Representative Selection via Graph Neural Networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2311.12727","title":"Soft Random Sampling: A Theoretical and Empirical Analysis","created":"2023-11-21","cited_by_count":2,"area":null},{"id":"2312.12574","title":"Generator Assisted Mixture of Experts For Feature Acquisition in Batch","created":"2023-12-19","cited_by_count":2,"area":"moe"},{"id":"2210.16892","title":"Partitioned Gradient Matching-based Data Subset Selection for Compute-Efficient Robust ASR Training","created":"2022-10-30","cited_by_count":1,"area":null},{"id":"2402.15472","title":"FAIR: Filtering of Automatically Induced Rules","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2402.16442","title":"On Distributed Larger-Than-Memory Subset Selection With Pairwise Submodular Functions","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2410.16115","title":"Increasing Interpretability of Neural Networks By Approximating Human Visual Saliency","created":"2024-10-21","cited_by_count":1,"area":null},{"id":"2511.01800","title":"Bayesian Coreset Optimization for Personalized Federated Learning","created":"2025-11-03","cited_by_count":1,"area":null},{"id":"2512.22385","title":"LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition","created":"2025-12-26","cited_by_count":1,"area":null},{"id":"2602.05162","title":"SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2605.12872","title":"SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2607.00144","title":"A Mechanism-Driven Theory of Phase Transitions in Active Learning","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2203.10365","title":"Domain Representative Keywords Selection: A Probabilistic Approach","created":"2022-03-19","cited_by_count":0,"area":null},{"id":"2402.18742","title":"Comparing Importance Sampling Based Methods for Mitigating the Effect of Class Imbalance","created":"2024-02-28","cited_by_count":0,"area":null},{"id":"2409.10641","title":"HAVANA: Hierarchical stochastic neighbor embedding for Accelerated Video ANnotAtions","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2501.10466","title":"Efficient Semi-Supervised Adversarial Training via Latent Clustering-Based Data Reduction","created":"2025-01-15","cited_by_count":0,"area":null},{"id":"2502.11085","title":"On the Importance of Pretraining Data Alignment for Atomic Property Prediction","created":"2025-02-16","cited_by_count":0,"area":null},{"id":"2503.06732","title":"Data Efficient Subset Training with Differential Privacy","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2603.23159","title":"Conformal Cross-Modal Active Learning","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2607.27660","title":"Understanding Submodular Information Measure Based Objectives for Representation Learning: A Variance and Separation Perspective","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2610.01282","title":"Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logistics","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}