{"list":"other","total":62,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"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":"2205.14959","title":"Dataset Condensation via Efficient Synthetic-Data Parameterization","created":"2022-05-30","cited_by_count":188},{"id":"2301.07014","title":"Dataset Distillation: A Comprehensive Review","created":"2023-01-17","cited_by_count":127},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117},{"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":"2302.14416","title":"DREAM: Efficient Dataset Distillation by Representative Matching","created":"2023-02-28","cited_by_count":94},{"id":"2301.04272","title":"Data Distillation: A Survey","created":"2023-01-11","cited_by_count":87},{"id":"2311.15529","title":"Efficient Dataset Distillation via Minimax Diffusion","created":"2023-11-27","cited_by_count":83},{"id":"1612.00804","title":"Restricted Strong Convexity Implies Weak Submodularity","created":"2016-12-02","cited_by_count":52},{"id":"2312.15927","title":"M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy","created":"2023-12-26","cited_by_count":49},{"id":"2308.10524","title":"Dataset Quantization","created":"2023-08-21","cited_by_count":48},{"id":"2211.08775","title":"Unbalanced Optimal Transport, from Theory to Numerics","created":"2022-11-16","cited_by_count":46},{"id":"2502.20653","title":"Dataset Distillation with Neural Characteristic Function: A Minmax Perspective","created":"2025-02-28","cited_by_count":45},{"id":"2404.13733","title":"Elucidating the Design Space of Dataset Condensation","created":"2024-04-21","cited_by_count":40},{"id":"2311.13613","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","created":"2023-11-22","cited_by_count":38},{"id":"2304.04521","title":"GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection","created":"2023-04-10","cited_by_count":36},{"id":"2412.14528","title":"Multi-Level Optimal Transport for Universal Cross-Tokenizer Knowledge Distillation on Language Models","created":"2024-12-19","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":"2502.05673","title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","created":"2025-02-08","cited_by_count":26},{"id":"2310.04470","title":"Hierarchical Multi-Marginal Optimal Transport for Network Alignment","created":"2023-10-06","cited_by_count":24},{"id":"2406.19827","title":"Towards Stable and Storage-efficient Dataset Distillation: Matching Convexified Trajectory","created":"2024-06-28","cited_by_count":21},{"id":"2212.08049","title":"Sliced Optimal Partial Transport","created":"2022-12-15","cited_by_count":20},{"id":"2411.19946","title":"DELT: A Simple Diversity-driven EarlyLate Training for Dataset Distillation","created":"2024-11-29","cited_by_count":20},{"id":"2410.17193","title":"Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios","created":"2024-10-22","cited_by_count":18},{"id":"2506.01413","title":"Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models","created":"2025-06-02","cited_by_count":17},{"id":"2402.17110","title":"Sinkhorn Distance Minimization for Knowledge Distillation","created":"2024-02-27","cited_by_count":15},{"id":"2505.24623","title":"Hyperbolic Dataset Distillation","created":"2025-05-30","cited_by_count":15},{"id":"2501.07575","title":"Dataset Distillation via Committee Voting","created":"2025-01-13","cited_by_count":14},{"id":"2407.07268","title":"Dataset Quantization with Active Learning based Adaptive Sampling","created":"2024-07-09","cited_by_count":13},{"id":"1311.2110","title":"Curvature and Optimal Algorithms for Learning and Minimizing Submodular Functions","created":"2013-11-08","cited_by_count":12},{"id":"2501.18901","title":"Lightspeed Geometric Dataset Distance via Sliced Optimal Transport","created":"2025-01-31","cited_by_count":10},{"id":"2408.14506","title":"Distilling Long-tailed Datasets","created":"2024-08-24","cited_by_count":9},{"id":"2412.16895","title":"Adaptive Dataset Quantization","created":"2024-12-22","cited_by_count":9},{"id":"2302.03232","title":"Linear Optimal Partial Transport Embedding","created":"2023-02-07","cited_by_count":8},{"id":"2408.01089","title":"Prototypical Partial Optimal Transport for Universal Domain Adaptation","created":"2024-08-02","cited_by_count":7},{"id":"2309.14091","title":"On the Benefit of Optimal Transport for Curriculum Reinforcement Learning","created":"2023-09-25","cited_by_count":6},{"id":"2310.15052","title":"DREAM+: Efficient Dataset Distillation by Bidirectional Representative Matching","created":"2023-10-23","cited_by_count":6},{"id":"2501.05635","title":"Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport","created":"2025-01-10","cited_by_count":6},{"id":"2503.08155","title":"Domain Adaptation and Entanglement: an Optimal Transport Perspective","created":"2025-03-11","cited_by_count":6},{"id":"2106.02835","title":"On the Role of Entropy-based Loss for Learning Causal Structures with Continuous Optimization","created":"2021-06-05","cited_by_count":5},{"id":"2401.07572","title":"Exploiting GPT-4 Vision for Zero-shot Point Cloud Understanding","created":"2024-01-15","cited_by_count":5},{"id":"2508.01139","title":"Dataset Condensation with Color Compensation","created":"2025-08-02","cited_by_count":5},{"id":"2512.00308","title":"Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation","created":"2025-11-29","cited_by_count":5},{"id":"2501.06405","title":"FocusDD: Real-World Scene Infusion for Robust Dataset Distillation","created":"2025-01-11","cited_by_count":4},{"id":"2502.12793","title":"Unsupervised Anomaly Detection through Mass Repulsing Optimal Transport","created":"2025-02-18","cited_by_count":4},{"id":"2505.07858","title":"Scaling Laws for Speculative Decoding","created":"2025-05-08","cited_by_count":4},{"id":"2108.11080","title":"Heredity-aware Child Face Image Generation with Latent Space Disentanglement","created":"2021-08-25","cited_by_count":3},{"id":"2506.01942","title":"OD3: Optimization-free Dataset Distillation for Object Detection","created":"2025-06-02","cited_by_count":3},{"id":"2511.18858","title":"Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling","created":"2025-11-24","cited_by_count":3},{"id":"2512.08317","title":"GeoDM: Geometry-aware Distribution Matching for Dataset Distillation","created":"2025-12-09","cited_by_count":3}],"next_cursor":null}