{"list":"other","total":67,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1812.05159","title":"An Empirical Study of Example Forgetting during Deep Neural Network Learning","created":"2018-12-12","cited_by_count":678},{"id":"2107.07075","title":"Deep Learning on a Data Diet: Finding Important Examples Early in Training","created":"2021-07-15","cited_by_count":533},{"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":"2110.04181","title":"Dataset Condensation with Distribution Matching","created":"2021-10-08","cited_by_count":365},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"1906.11829","title":"Selection via Proxy: Efficient Data Selection for Deep Learning","created":"2019-06-26","cited_by_count":339},{"id":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"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},{"id":"2011.00050","title":"Dataset Meta-Learning from Kernel Ridge-Regression","created":"2020-10-30","cited_by_count":230},{"id":"2012.10630","title":"GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learning","created":"2020-12-19","cited_by_count":226},{"id":"2107.13034","title":"Dataset Distillation with Infinitely Wide Convolutional Networks","created":"2021-07-27","cited_by_count":218},{"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":"1802.09841","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","created":"2018-02-27","cited_by_count":158},{"id":"2109.03764","title":"Active Learning by Acquiring Contrastive Examples","created":"2021-09-08","cited_by_count":156},{"id":"2204.08499","title":"DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning","created":"2022-04-18","cited_by_count":147},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"id":"2008.05723","title":"Contextual Diversity for Active Learning","created":"2020-08-13","cited_by_count":139},{"id":"2306.13092","title":"Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective","created":"2023-06-22","cited_by_count":138},{"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":"2307.09742","title":"Improved Distribution Matching for Dataset Condensation","created":"2023-07-19","cited_by_count":124},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2301.05603","title":"A Comprehensive Survey of Dataset Distillation","created":"2023-01-13","cited_by_count":115},{"id":"2210.12067","title":"Efficient Dataset Distillation Using Random Feature Approximation","created":"2022-10-21","cited_by_count":111},{"id":"2206.02916","title":"Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks","created":"2022-06-06","cited_by_count":104},{"id":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2403.19522","title":"Model Stock: All we need is just a few fine-tuned models","created":"2024-03-28","cited_by_count":92},{"id":"2006.15412","title":"Submodular Combinatorial Information Measures with Applications in Machine Learning","created":"2020-06-27","cited_by_count":88},{"id":"2310.00093","title":"DataDAM: Efficient Dataset Distillation with Attention Matching","created":"2023-09-29","cited_by_count":84},{"id":"2204.07513","title":"Synthesizing Informative Training Samples with GAN","created":"2022-04-15","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":"2207.09639","title":"DC-BENCH: Dataset Condensation Benchmark","created":"2022-07-20","cited_by_count":67},{"id":"2212.06152","title":"Accelerating Dataset Distillation via Model Augmentation","created":"2022-12-12","cited_by_count":62},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2302.06755","title":"Dataset Distillation with Convexified Implicit Gradients","created":"2023-02-13","cited_by_count":46},{"id":"2208.10494","title":"Dataset Condensation with Latent Space Knowledge Factorization and Sharing","created":"2022-08-21","cited_by_count":34},{"id":"2311.18531","title":"Dataset Distillation via the Wasserstein Metric","created":"2023-11-30","cited_by_count":31},{"id":"2404.00563","title":"Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation","created":"2024-03-31","cited_by_count":31},{"id":"2311.08819","title":"Frequency Domain-based Dataset Distillation","created":"2023-11-15","cited_by_count":28},{"id":"2311.18838","title":"Dataset Distillation via Curriculum Data Synthesis in Large Data Era","created":"2023-11-30","cited_by_count":26},{"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":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2310.14019","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","created":"2023-10-21","cited_by_count":20},{"id":"2506.23580","title":"Dataset Distillation via Vision-Language Category Prototype","created":"2025-06-30","cited_by_count":19},{"id":"2406.03793","title":"Low-Rank Similarity Mining for Multimodal Dataset Distillation","created":"2024-06-06","cited_by_count":17},{"id":"2406.01063","title":"DANCE: Dual-View Distribution Alignment for Dataset Condensation","created":"2024-06-03","cited_by_count":15},{"id":"2210.06205","title":"On Divergence Measures for Bayesian Pseudocoresets","created":"2022-10-12","cited_by_count":10},{"id":"2509.15472","title":"Efficient Multimodal Dataset Distillation via Generative Models","created":"2025-09-18","cited_by_count":7},{"id":"2407.08113","title":"FYI: Flip Your Images for Dataset Distillation","created":"2024-07-11","cited_by_count":4},{"id":"2505.11216","title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","created":"2025-05-16","cited_by_count":2},{"id":"2507.17221","title":"Dataset Distillation as Data Compression: A Rate-Utility Perspective","created":"2025-07-23","cited_by_count":2}],"next_cursor":null}