{"list":"other","total":51,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2404.06395","title":"MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies","created":"2024-04-09","cited_by_count":723},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"1804.06561","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","created":"2018-04-18","cited_by_count":466},{"id":"2103.00065","title":"Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability","created":"2021-02-26","cited_by_count":427},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2103.03841","title":"Generating Images with Sparse Representations","created":"2021-03-05","cited_by_count":266},{"id":"2402.17245","title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","created":"2024-02-27","cited_by_count":256},{"id":"2003.02218","title":"The large learning rate phase of deep learning: the catapult mechanism","created":"2020-03-04","cited_by_count":216},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183},{"id":"1907.04595","title":"Towards Explaining the Regularization Effect of Initial Large Learning Rate in Training Neural Networks","created":"2019-07-10","cited_by_count":162},{"id":"2405.04233","title":"Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models","created":"2024-05-07","cited_by_count":160},{"id":"2007.15801","title":"Finite Versus Infinite Neural Networks: an Empirical Study","created":"2020-07-31","cited_by_count":157},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154},{"id":"1910.12478","title":"Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes","created":"2019-10-28","cited_by_count":151},{"id":"2305.18619","title":"Likelihood-Based Diffusion Language Models","created":"2023-05-30","cited_by_count":151},{"id":"2006.14548","title":"Tensor Programs II: Neural Tangent Kernel for Any Architecture","created":"2020-06-25","cited_by_count":143},{"id":"2304.03208","title":"Cerebras-GPT: Open Compute-Optimal Language Models Trained on the Cerebras Wafer-Scale Cluster","created":"2023-04-06","cited_by_count":109},{"id":"2310.02244","title":"Tensor Programs VI: Feature Learning in Infinite-Depth Neural Networks","created":"2023-10-03","cited_by_count":97},{"id":"2502.15894","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","created":"2025-02-21","cited_by_count":66},{"id":"2105.03703","title":"Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics","created":"2021-05-08","cited_by_count":57},{"id":"2201.10469","title":"Convex Analysis of the Mean Field Langevin Dynamics","created":"2022-01-25","cited_by_count":55},{"id":"2009.10685","title":"Tensor Programs III: Neural Matrix Laws","created":"2020-09-22","cited_by_count":49},{"id":"2405.15712","title":"Infinite Limits of Multi-head Transformer Dynamics","created":"2024-05-24","cited_by_count":39},{"id":"2308.01814","title":"Tensor Programs IVb: Adaptive Optimization in the Infinite-Width Limit","created":"2023-08-03","cited_by_count":38},{"id":"2404.02883","title":"On the Scalability of Diffusion-based Text-to-Image Generation","created":"2024-04-03","cited_by_count":36},{"id":"2302.02334","title":"Revisiting Discriminative vs. Generative Classifiers: Theory and Implications","created":"2023-02-05","cited_by_count":29},{"id":"2407.17465","title":"u-$\\mu$P: The Unit-Scaled Maximal Update Parametrization","created":"2024-07-24","cited_by_count":29},{"id":"2305.17476","title":"Toward Understanding Generative Data Augmentation","created":"2023-05-27","cited_by_count":25},{"id":"2409.15156","title":"Rethinking Conventional Wisdom in Machine Learning: From Generalization to Scaling","created":"2024-09-23","cited_by_count":23},{"id":"2309.03852","title":"FLM-101B: An Open LLM and How to Train It with $100K Budget","created":"2023-09-07","cited_by_count":22},{"id":"2411.17470","title":"Towards Precise Scaling Laws for Video Diffusion Transformers","created":"2024-11-25","cited_by_count":20},{"id":"2409.19345","title":"Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization","created":"2024-09-28","cited_by_count":17},{"id":"2404.16645","title":"Tele-FLM Technical Report","created":"2024-04-25","cited_by_count":12},{"id":"2411.00075","title":"{\\mu}P$^2$: Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling","created":"2024-10-31","cited_by_count":10},{"id":"2405.16845","title":"On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability","created":"2024-05-27","cited_by_count":5},{"id":"2406.19853","title":"YuLan: An Open-source Large Language Model","created":"2024-06-28","cited_by_count":4},{"id":"2502.14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","created":"2025-02-20","cited_by_count":1}],"next_cursor":null}