{"list":"other","total":72,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2206.00719","title":"Dataset Distillation using Neural Feature Regression","created":"2022-06-01","cited_by_count":177},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2305.01649","title":"Generalizing Dataset Distillation via Deep Generative Prior","created":"2023-05-02","cited_by_count":126},{"id":"2310.05773","title":"Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching","created":"2023-10-09","cited_by_count":118},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"id":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"id":"2402.05123","title":"A Survey on Data Selection for LLM Instruction Tuning","created":"2024-02-04","cited_by_count":77},{"id":"2407.15138","title":"D$^4$M: Dataset Distillation via Disentangled Diffusion Model","created":"2024-07-21","cited_by_count":77},{"id":"2306.05175","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","created":"2023-06-08","cited_by_count":63},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36},{"id":"2305.01975","title":"A Survey on Dataset Distillation: Approaches, Applications and Future Directions","created":"2023-05-03","cited_by_count":32},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31},{"id":"2407.14245","title":"Dataset Distillation by Automatic Training Trajectories","created":"2024-07-19","cited_by_count":26},{"id":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26},{"id":"2504.14772","title":"Knowledge Distillation and Dataset Distillation of Large Language Models: Emerging Trends, Challenges, and Future Directions","created":"2025-04-20","cited_by_count":26},{"id":"1607.03463","title":"LazySVD: Even Faster SVD Decomposition Yet Without Agonizing Pain","created":"2016-07-12","cited_by_count":22},{"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},{"id":"2410.09335","title":"Rethinking Data Selection at Scale: Random Selection is Almost All You Need","created":"2024-10-12","cited_by_count":22},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2510.13721","title":"NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching","created":"2025-10-15","cited_by_count":21},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19},{"id":"2507.17343","title":"Principled Multimodal Representation Learning","created":"2025-07-23","cited_by_count":19},{"id":"2404.09161","title":"Coreset Selection for Object Detection","created":"2024-04-14","cited_by_count":18},{"id":"2406.03793","title":"Low-Rank Similarity Mining for Multimodal Dataset Distillation","created":"2024-06-06","cited_by_count":17},{"id":"2301.03344","title":"Universal Multimodal Representation for Language Understanding","created":"2023-01-09","cited_by_count":14},{"id":"2311.08675","title":"Refined Coreset Selection: Towards Minimal Coreset Size under Model Performance Constraints","created":"2023-11-15","cited_by_count":13},{"id":"2406.05704","title":"Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset Distillation","created":"2024-06-09","cited_by_count":13},{"id":"2603.06577","title":"Omni-Diffusion: Unified Multimodal Understanding and Generation with Masked Discrete Diffusion","created":"2026-03-06","cited_by_count":13},{"id":"2310.08782","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","created":"2023-10-13","cited_by_count":11},{"id":"2602.24144","title":"Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation","created":"2026-02-27","cited_by_count":11},{"id":"2502.17607","title":"Synthetic Text Generation for Training Large Language Models via Gradient Matching","created":"2025-02-24","cited_by_count":10},{"id":"2211.11923","title":"On Optimal Coreset Construction for Euclidean $(k,z)$-Clustering","created":"2022-11-22","cited_by_count":9},{"id":"2504.20500","title":"UniDetox: Universal Detoxification of Large Language Models via Dataset Distillation","created":"2025-04-29","cited_by_count":8},{"id":"2505.14705","title":"Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation","created":"2025-05-16","cited_by_count":7},{"id":"2509.15472","title":"Efficient Multimodal Dataset Distillation via Generative Models","created":"2025-09-18","cited_by_count":7},{"id":"2511.17890","title":"Decoupled Audio-Visual Dataset Distillation","created":"2025-11-22","cited_by_count":7},{"id":"2410.02116","title":"Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks","created":"2024-10-03","cited_by_count":6},{"id":"2406.06609","title":"Mitigating Bias in Dataset Distillation","created":"2024-06-06","cited_by_count":4},{"id":"2412.20964","title":"Hierarchical Banzhaf Interaction for General Video-Language Representation Learning","created":"2024-12-30","cited_by_count":4},{"id":"2503.14112","title":"Condensing Action Segmentation Datasets via Generative Network Inversion","created":"2025-03-18","cited_by_count":4},{"id":"2511.16674","title":"Dataset Distillation for Pre-Trained Self-Supervised Vision Models","created":"2025-11-20","cited_by_count":4},{"id":"2510.17421","title":"Diffusion Models as Dataset Distillation Priors","created":"2025-10-20","cited_by_count":3},{"id":"2510.18583","title":"CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder","created":"2025-10-21","cited_by_count":3},{"id":"2505.22564","title":"PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion","created":"2025-05-28","cited_by_count":2},{"id":"2509.24177","title":"High-Order Progressive Trajectory Matching for Medical Image Dataset Distillation","created":"2025-09-29","cited_by_count":2},{"id":"2507.21455","title":"Boost Self-Supervised Dataset Distillation via Parameterization, Predefined Augmentation, and Approximation","created":"2025-07-29","cited_by_count":1}],"next_cursor":null}