{"total":99,"rows":[{"id":"2107.14263","title":"Batch Active Learning at Scale","created":"2021-07-29","cited_by_count":127,"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":"2311.14736","title":"Data Diversity Matters for Robust Instruction Tuning","created":"2023-11-21","cited_by_count":76,"area":null},{"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":"2207.13887","title":"Adaptive Second Order Coresets for Data-efficient Machine Learning","created":"2022-07-28","cited_by_count":60,"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":"2305.18761","title":"Identifying Spurious Biases Early in Training through the Lens of Simplicity Bias","created":"2023-05-30","cited_by_count":44,"area":null},{"id":"2210.09671","title":"Not All Poisons are Created Equal: Robust Training against Data Poisoning","created":"2022-10-18","cited_by_count":30,"area":"safety"},{"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":"2203.04940","title":"Data-Efficient Structured Pruning via Submodular Optimization","created":"2022-03-09","cited_by_count":23,"area":null},{"id":"2401.06692","title":"An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models","created":"2024-01-12","cited_by_count":23,"area":null},{"id":"2302.09195","title":"Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least","created":"2023-02-18","cited_by_count":22,"area":null},{"id":"2312.08057","title":"Combinatorial Stochastic-Greedy Bandit","created":"2023-12-13","cited_by_count":18,"area":null},{"id":"2509.10918","title":"ToMA: Token Merge with Attention for Diffusion Models","created":"2025-09-13","cited_by_count":18,"area":"diffusion"},{"id":"2305.08367","title":"Toward Highly Efficient and Private Submodular Maximization via Matrix-Based Acceleration","created":"2023-05-15","cited_by_count":11,"area":null},{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11,"area":null},{"id":"2103.13090","title":"Greedy-Based Feature Selection for Efficient LiDAR SLAM","created":"2021-03-24","cited_by_count":9,"area":null},{"id":"2104.01750","title":"Optimal Sampling Gaps for Adaptive Submodular Maximization","created":"2021-04-05","cited_by_count":9,"area":null},{"id":"2202.03051","title":"Using Partial Monotonicity in Submodular Maximization","created":"2022-02-07","cited_by_count":9,"area":null},{"id":"2210.01520","title":"CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification","created":"2022-10-04","cited_by_count":9,"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":"2103.00384","title":"Adaptive Regularized Submodular Maximization","created":"2021-02-28","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":"2305.06408","title":"Accelerating Batch Active Learning Using Continual Learning Techniques","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2403.14772","title":"Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures","created":"2024-03-21","cited_by_count":8,"area":null},{"id":"2512.25052","title":"AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAG","created":"2025-12-31","cited_by_count":8,"area":"rag"},{"id":"2106.05484","title":"A Unified Framework for Task-Driven Data Quality Management","created":"2021-06-10","cited_by_count":7,"area":null},{"id":"2304.04389","title":"Deep Active Alignment of Knowledge Graph Entities and Schemata","created":"2023-04-10","cited_by_count":7,"area":null},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","cited_by_count":7,"area":"distill"},{"id":"2109.05975","title":"Balancing the Budget: Feature Selection and Tracking for Multi-Camera Visual-Inertial Odometry","created":"2021-09-13","cited_by_count":6,"area":null},{"id":"2206.08566","title":"Active Data Discovery: Mining Unknown Data using Submodular Information Measures","created":"2022-06-17","cited_by_count":6,"area":null},{"id":"2401.00403","title":"Overcome Modal Bias in Multi-modal Federated Learning via Balanced Modality Selection","created":"2023-12-31","cited_by_count":6,"area":null},{"id":"2104.11843","title":"One-Round Active Learning","created":"2021-04-23","cited_by_count":5,"area":null},{"id":"2206.05947","title":"Lazy and Fast Greedy MAP Inference for Determinantal Point Process","created":"2022-06-13","cited_by_count":5,"area":null},{"id":"2305.02806","title":"Maximizing Submodular Functions for Recommendation in the Presence of Biases","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2305.10292","title":"Linear Query Approximation Algorithms for Non-monotone Submodular Maximization under Knapsack Constraint","created":"2023-05-17","cited_by_count":5,"area":null},{"id":"2306.04454","title":"Training-Free Neural Active Learning with Initialization-Robustness Guarantees","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2406.04914","title":"Submodular Framework for Structured-Sparse Optimal Transport","created":"2024-06-07","cited_by_count":5,"area":null},{"id":"2605.02209","title":"Submodular Benchmark Selection","created":"2026-05-04","cited_by_count":5,"area":null},{"id":"2608.05810","title":"When Self-Evolution Backfires: Pre-Commit Gating against Skill Contamination in LLM Agents","created":"2026-08-06","cited_by_count":5,"area":"agents"},{"id":"2107.05978","title":"DIVINE: Diverse Influential Training Points for Data Visualization and Model Refinement","created":"2021-07-13","cited_by_count":4,"area":null},{"id":"2107.11333","title":"Robust Adaptive Submodular Maximization","created":"2021-07-23","cited_by_count":4,"area":null},{"id":"2202.03593","title":"Nonmyopic Multiclass Active Search with Diminishing Returns for Diverse Discovery","created":"2022-02-08","cited_by_count":4,"area":null},{"id":"2210.08363","title":"Data-Efficient Augmentation for Training Neural Networks","created":"2022-10-15","cited_by_count":4,"area":null},{"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":"2102.11932","title":"On Meritocracy in Optimal Set Selection","created":"2021-02-23","cited_by_count":3,"area":null},{"id":"2201.07289","title":"Sparsification of Decomposable Submodular Functions","created":"2022-01-18","cited_by_count":3,"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":"2212.09483","title":"Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning","created":"2022-12-19","cited_by_count":3,"area":null},{"id":"2405.13994","title":"Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2102.06486","title":"Adaptive Sampling for Fast Constrained Maximization of Submodular Function","created":"2021-02-12","cited_by_count":2,"area":null},{"id":"2102.11911","title":"Instance Specific Approximations for Submodular Maximization","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2104.02772","title":"The Power of Subsampling in Submodular Maximization","created":"2021-04-06","cited_by_count":2,"area":null},{"id":"2111.14674","title":"Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes","created":"2021-11-29","cited_by_count":2,"area":null},{"id":"2211.00980","title":"Balancing Utility and Fairness in Submodular Maximization (Technical Report)","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2305.06677","title":"INGENIOUS: Using Informative Data Subsets for Efficient Pre-Training of Language Models","created":"2023-05-11","cited_by_count":2,"area":null},{"id":"2305.10643","title":"STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings","created":"2023-05-18","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":"2405.07083","title":"Data-Efficient and Robust Task Selection for Meta-Learning","created":"2024-05-11","cited_by_count":2,"area":null},{"id":"2604.10952","title":"UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees","created":"2026-04-13","cited_by_count":2,"area":null},{"id":"2605.27858","title":"DecomposeRL: Learning to Ask Useful, Informative, and Diverse Questions for Semi-Supervised, Traceable Claim Verification","created":"2026-05-27","cited_by_count":2,"area":null},{"id":"2607.09739","title":"Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2101.07423","title":"Submodular Maximization via Taylor Series Approximation","created":"2021-01-19","cited_by_count":1,"area":null},{"id":"2107.06703","title":"Zero-Round Active Learning","created":"2021-07-14","cited_by_count":1,"area":null},{"id":"2111.10175","title":"Randomized Algorithms for Monotone Submodular Function Maximization on the Integer Lattice","created":"2021-11-19","cited_by_count":1,"area":null},{"id":"2206.09563","title":"Scalable Distributed Algorithms for Size-Constrained Submodular Maximization in the MapReduce and Adaptive Complexity Models","created":"2022-06-20","cited_by_count":1,"area":null},{"id":"2210.01526","title":"DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures","created":"2022-10-04","cited_by_count":1,"area":null},{"id":"2401.12478","title":"Mini-batch Submodular Maximization","created":"2024-01-23","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":"2404.03759","title":"Localized Distributional Robustness in Submodular Multi-Task Subset Selection","created":"2024-04-04","cited_by_count":1,"area":null},{"id":"2408.13683","title":"Submodular Maximization Approaches for Equitable Client Selection in Federated Learning","created":"2024-08-24","cited_by_count":1,"area":null},{"id":"2506.07747","title":"E-LDA: Toward Interpretable LDA Topic Models with Strong Guarantees in Logarithmic Parallel Time","created":"2025-06-06","cited_by_count":1,"area":null},{"id":"2508.21003","title":"InSQuAD: In-Context Learning for Efficient Retrieval via Submodular Mutual Information to Enforce Quality and Diversity","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2510.07064","title":"Prompt Optimization Across Multiple Agents for Representing Diverse Human Populations","created":"2025-10-08","cited_by_count":1,"area":"agents"},{"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":"2604.11328","title":"Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees","created":"2026-04-13","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":"2606.18008","title":"PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution","created":"2026-06-16","cited_by_count":1,"area":"mllm"},{"id":"2201.10547","title":"Optimal Data Selection: An Online Distributed View","created":"2022-01-25","cited_by_count":0,"area":null},{"id":"2203.05651","title":"BASIL: Balanced Active Semi-supervised Learning for Class Imbalanced Datasets","created":"2022-03-10","cited_by_count":0,"area":null},{"id":"2210.01860","title":"ProtoBandit: Efficient Prototype Selection via Multi-Armed Bandits","created":"2022-10-04","cited_by_count":0,"area":null},{"id":"2306.15848","title":"Ordering for Non-Replacement SGD","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2310.17870","title":"Ranking with Slot Constraints","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2402.13468","title":"STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning","created":"2024-02-21","cited_by_count":0,"area":null},{"id":"2406.14876","title":"Training Greedy Policy for Proposal Batch Selection in Expensive Multi-Objective Combinatorial Optimization","created":"2024-06-21","cited_by_count":0,"area":null},{"id":"2409.03545","title":"The Power of Second Chance: Personalized Submodular Maximization with Two Candidates","created":"2024-09-05","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":"2509.10390","title":"Vendi Information Gain for Active Learning and its Application to Ecology","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2510.02470","title":"SAGE: Streaming Agreement-Driven Gradient Sketches for Representative Subset Selection","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2510.22517","title":"Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2601.01695","title":"Learnability-Driven Submodular Optimization for Active Roadside 3D Detection","created":"2026-01-04","cited_by_count":0,"area":null},{"id":"2601.10067","title":"Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2602.16183","title":"Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedback","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2604.03419","title":"Adaptive Threshold-Driven Continuous Greedy Method for Scalable Submodular Optimization","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2608.01502","title":"Stochastic Sequential Search in Very-High-Dimensional Feature Selection","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.23252","title":"The Laws of Context Allocation: Causal Measurement and Closed-Loop Orchestration in Generative Search","created":"2026-08-24","cited_by_count":0,"area":"rag"},{"id":"2609.30393","title":"LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.14028","title":"Pick the Mixture, Not the Samples: Combinatorial Data Selection for LLMs","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.17530","title":"TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models","created":"2026-10-13","cited_by_count":0,"area":"mllm"}],"next_cursor":null}