{"total":36,"rows":[{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135,"area":null},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118,"area":null},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77,"area":null},{"id":"2310.09192","title":"Does Graph Distillation See Like Vision Dataset Counterpart?","created":"2023-10-13","cited_by_count":45,"area":null},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40,"area":null},{"id":"2502.01968","title":"Token Cleaning: Fine-Grained Data Selection for LLM Supervised Fine-Tuning","created":"2025-02-04","cited_by_count":39,"area":null},{"id":"2311.13613","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","created":"2023-11-22","cited_by_count":38,"area":null},{"id":"2410.10877","title":"Improving Data Efficiency via Curating LLM-Driven Rating Systems","created":"2024-10-09","cited_by_count":29,"area":null},{"id":"2402.05011","title":"Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching","created":"2024-02-07","cited_by_count":28,"area":null},{"id":"2406.18561","title":"SelMatch: Effectively Scaling Up Dataset Distillation via Selection-Based Initialization and Partial Updates by Trajectory Matching","created":"2024-05-28","cited_by_count":22,"area":null},{"id":"2309.07698","title":"Dataset Condensation via Generative Model","created":"2023-09-14","cited_by_count":15,"area":null},{"id":"2406.01063","title":"DANCE: Dual-View Distribution Alignment for Dataset Condensation","created":"2024-06-03","cited_by_count":15,"area":null},{"id":"2408.02193","title":"CodeACT: Code Adaptive Compute-efficient Tuning Framework for Code LLMs","created":"2024-08-05","cited_by_count":15,"area":null},{"id":"2407.07268","title":"Dataset Quantization with Active Learning based Adaptive Sampling","created":"2024-07-09","cited_by_count":13,"area":null},{"id":"2310.03295","title":"Can pre-trained models assist in dataset distillation?","created":"2023-10-05","cited_by_count":12,"area":null},{"id":"2311.15547","title":"Dataset Distillation in Latent Space","created":"2023-11-27","cited_by_count":8,"area":null},{"id":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2508.21589","title":"Middo: Model-Informed Dynamic Data Optimization for Enhanced LLM Fine-Tuning via Closed-Loop Learning","created":"2025-08-29","cited_by_count":7,"area":null},{"id":"2504.12687","title":"Data-efficient LLM Fine-tuning for Code Generation","created":"2025-04-17","cited_by_count":5,"area":null},{"id":"2505.11882","title":"GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencoder","created":"2025-05-17","cited_by_count":5,"area":null},{"id":"2508.04329","title":"Forgetting: A New Mechanism Towards Better Large Language Model Fine-tuning","created":"2025-08-06","cited_by_count":4,"area":null},{"id":"2405.01373","title":"ATOM: Attention Mixer for Efficient Dataset Distillation","created":"2024-05-02","cited_by_count":3,"area":null},{"id":"2505.18358","title":"CONCORD: Concept-Informed Diffusion for Dataset Distillation","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2508.02313","title":"NMS: Efficient Edge DNN Training via Near-Memory Sampling on Manifolds","created":"2025-08-04","cited_by_count":3,"area":null},{"id":"2402.03158","title":"Optimal and Near-Optimal Adaptive Vector Quantization","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2402.05356","title":"Exploring Learning Complexity for Efficient Downstream Dataset Pruning","created":"2024-02-08","cited_by_count":2,"area":null},{"id":"2602.05414","title":"TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions","created":"2026-02-05","cited_by_count":2,"area":null},{"id":"2503.13383","title":"Cream of the Crop: Harvesting Rich, Scalable and Transferable Multi-Modal Data for Instruction Fine-Tuning","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2504.09818","title":"Transferable text data distillation by trajectory matching","created":"2025-04-14","cited_by_count":1,"area":null},{"id":"2508.16647","title":"AdapSNE: Adaptive Fireworks-Optimized and Entropy-Guided Dataset Sampling for Edge DNN Training","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2609.22894","title":"Are Coreset Selection Methods Worth Their Cost?","created":"2026-09-19","cited_by_count":1,"area":null},{"id":"2506.22190","title":"dreaMLearning: Data Compression Assisted Machine Learning","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2508.19659","title":"SCAR: A Characterization Scheme for Multi-Modal Dataset","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.18650","title":"Binary Quadratic Quantization: Beyond First-Order Quantization for Real-Valued Matrix Compression","created":"2025-10-21","cited_by_count":0,"area":null},{"id":"2511.04803","title":"Data Efficiency and Transfer Robustness in Biomedical Image Segmentation: A Study of Redundancy and Forgetting with Cellpose","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2602.20650","title":"Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression","created":"2026-02-24","cited_by_count":0,"area":null}],"next_cursor":null}