{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1702.08734","title":"Billion-scale similarity search with GPUs","created":"2017-02-28","cited_by_count":2497},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"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":"2102.08259","title":"Dataset Condensation with Differentiable Siamese Augmentation","created":"2021-02-16","cited_by_count":291},{"id":"2211.10586","title":"Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory","created":"2022-11-19","cited_by_count":181},{"id":"2211.11004","title":"Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation","created":"2022-11-20","cited_by_count":142},{"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":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","created":"2022-05-19","cited_by_count":133},{"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":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120},{"id":"2210.16774","title":"Dataset Distillation via Factorization","created":"2022-10-30","cited_by_count":115},{"id":"2310.03502","title":"Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion","created":"2023-10-05","cited_by_count":114},{"id":"2312.03526","title":"On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm","created":"2023-12-06","cited_by_count":109},{"id":"2202.02916","title":"Dataset Condensation with Contrastive Signals","created":"2022-02-07","cited_by_count":105},{"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":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"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":"2311.17950","title":"Generalized Large-Scale Data Condensation via Various Backbone and Statistical Matching","created":"2023-11-29","cited_by_count":69},{"id":"2104.02857","title":"Soft-Label Anonymous Gastric X-ray Image Distillation","created":"2021-04-07","cited_by_count":51},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2210.01738","title":"ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training","created":"2022-10-04","cited_by_count":47},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2211.04446","title":"Private Set Generation with Discriminative Information","created":"2022-11-07","cited_by_count":34},{"id":"2310.02110","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","created":"2023-10-03","cited_by_count":33},{"id":"2311.08819","title":"Frequency Domain-based Dataset Distillation","created":"2023-11-15","cited_by_count":28},{"id":"2312.04655","title":"ECLIPSE: A Resource-Efficient Text-to-Image Prior for Image Generations","created":"2023-12-07","cited_by_count":24},{"id":"2308.07545","title":"Vision-Language Dataset Distillation","created":"2023-08-15","cited_by_count":19},{"id":"2506.23580","title":"Dataset Distillation via Vision-Language Category Prototype","created":"2025-06-30","cited_by_count":19},{"id":"2505.18399","title":"Taming Diffusion for Dataset Distillation with High Representativeness","created":"2025-05-23","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":"2309.07698","title":"Dataset Condensation via Generative Model","created":"2023-09-14","cited_by_count":15},{"id":"2506.22637","title":"CaO$_2$: Rectifying Inconsistencies in Diffusion-Based Dataset Distillation","created":"2025-06-27","cited_by_count":14},{"id":"2403.02580","title":"What do we learn from inverting CLIP models?","created":"2024-03-05","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":"2408.06927","title":"Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator","created":"2024-08-13","cited_by_count":13},{"id":"2503.18267","title":"Enhancing Dataset Distillation via Non-Critical Region Refinement","created":"2025-03-24","cited_by_count":9},{"id":"2505.14705","title":"Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation","created":"2025-05-16","cited_by_count":7},{"id":"2310.07506","title":"Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensation","created":"2023-10-11","cited_by_count":6},{"id":"2503.04835","title":"Distilling Dataset into Neural Field","created":"2025-03-05","cited_by_count":5},{"id":"2312.05598","title":"Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study","created":"2023-12-09","cited_by_count":3},{"id":"2506.01586","title":"Multi-Modal Dataset Distillation in the Wild","created":"2025-06-02","cited_by_count":1}],"next_cursor":null}