{"list":"other","total":52,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2010.08895","title":"Fourier Neural Operator for Parametric Partial Differential Equations","created":"2020-10-18","cited_by_count":2908},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"1910.03193","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","created":"2019-10-08","cited_by_count":2018},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2010.03409","title":"Learning Mesh-Based Simulation with Graph Networks","created":"2020-10-07","cited_by_count":868},{"id":"2003.03485","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","created":"2020-03-07","cited_by_count":734},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2204.13902","title":"Fast Sampling of Diffusion Models with Exponential Integrator","created":"2022-04-29","cited_by_count":532},{"id":"1612.00222","title":"Interaction Networks for Learning about Objects, Relations and Physics","created":"2016-12-01","cited_by_count":509},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2101.02388","title":"Knowledge Distillation in Iterative Generative Models for Improved Sampling Speed","created":"2021-01-07","cited_by_count":348},{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"2309.00583","title":"Geometry-Informed Neural Operator for Large-Scale 3D PDEs","created":"2023-09-01","cited_by_count":303},{"id":"2111.13802","title":"Factorized Fourier Neural Operators","created":"2021-11-27","cited_by_count":249},{"id":"2405.19101","title":"Poseidon: Efficient Foundation Models for PDEs","created":"2024-05-29","cited_by_count":200},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197},{"id":"2403.03542","title":"DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training","created":"2024-03-06","cited_by_count":151},{"id":"1810.08217","title":"Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows","created":"2018-10-18","cited_by_count":150},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128},{"id":"2112.15275","title":"Learned Coarse Models for Efficient Turbulence Simulation","created":"2021-12-31","cited_by_count":91},{"id":"2407.07218","title":"Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations","created":"2024-07-09","cited_by_count":91},{"id":"2209.14855","title":"Continuous PDE Dynamics Forecasting with Implicit Neural Representations","created":"2022-09-29","cited_by_count":73},{"id":"2306.01776","title":"From Zero to Turbulence: Generative Modeling for 3D Flow Simulation","created":"2023-05-29","cited_by_count":49},{"id":"2406.02176","title":"AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields","created":"2024-06-04","cited_by_count":39},{"id":"2403.17728","title":"Masked Autoencoders are PDE Learners","created":"2024-03-26","cited_by_count":14},{"id":"2406.08473","title":"Strategies for Pretraining Neural Operators","created":"2024-06-12","cited_by_count":14},{"id":"2405.07395","title":"CaFA: Global Weather Forecasting with Factorized Attention on Sphere","created":"2024-05-12","cited_by_count":6},{"id":"2402.17853","title":"Latent Neural PDE Solver: a reduced-order modelling framework for partial differential equations","created":"2024-02-27","cited_by_count":5},{"id":"2405.04396","title":"Predicting Transonic Flowfields in Non-Homogeneous Unstructured Grids Using Autoencoder Graph Convolutional Networks","created":"2024-05-07","cited_by_count":2}],"next_cursor":null}