{"list":"other","total":65,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"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":"1706.02677","title":"Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour","created":"2017-06-08","cited_by_count":1492},{"id":"1910.07467","title":"Root Mean Square Layer Normalization","created":"2019-10-16","cited_by_count":1480},{"id":"2111.09883","title":"Swin Transformer V2: Scaling Up Capacity and Resolution","created":"2021-11-18","cited_by_count":1228},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2003.03485","title":"Neural Operator: Graph Kernel Network for Partial Differential Equations","created":"2020-03-07","cited_by_count":734},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2111.03794","title":"Physics-Informed Neural Operator for Learning Partial Differential Equations","created":"2021-11-06","cited_by_count":527},{"id":"2209.12152","title":"All are Worth Words: A ViT Backbone for Diffusion Models","created":"2022-09-25","cited_by_count":502},{"id":"2102.01010","title":"Machine learning accelerated computational fluid dynamics","created":"2021-01-28","cited_by_count":471},{"id":"2301.11093","title":"Simple diffusion: End-to-end diffusion for high resolution images","created":"2023-01-26","cited_by_count":422},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"2105.14995","title":"Choose a Transformer: Fourier or Galerkin","created":"2021-05-31","cited_by_count":343},{"id":"2402.02366","title":"Transolver: A Fast Transformer Solver for PDEs on General Geometries","created":"2024-02-04","cited_by_count":326},{"id":"2205.13671","title":"Transformer for Partial Differential Equations' Operator Learning","created":"2022-05-26","cited_by_count":283},{"id":"2403.14735","title":"Foundation Models for Time Series Analysis: A Tutorial and Survey","created":"2024-03-21","cited_by_count":239},{"id":"2311.05556","title":"LCM-LoRA: A Universal Stable-Diffusion Acceleration Module","created":"2023-11-09","cited_by_count":211},{"id":"2007.00016","title":"Solver-in-the-Loop: Learning from Differentiable Physics to Interact with Iterative PDE-Solvers","created":"2020-06-30","cited_by_count":205},{"id":"2209.15616","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","created":"2022-09-30","cited_by_count":197},{"id":"2412.00568","title":"The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning","created":"2024-11-30","cited_by_count":145},{"id":"2304.06027","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","created":"2023-04-12","cited_by_count":141},{"id":"2306.00258","title":"Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior","created":"2023-06-01","cited_by_count":131},{"id":"2305.17560","title":"Scalable Transformer for PDE Surrogate Modeling","created":"2023-05-27","cited_by_count":128},{"id":"1806.02071","title":"Deep Fluids: A Generative Network for Parameterized Fluid Simulations","created":"2018-06-06","cited_by_count":121},{"id":"2310.17513","title":"The Expressive Power of Low-Rank Adaptation","created":"2023-10-26","cited_by_count":102},{"id":"2304.07993","title":"In-Context Operator Learning with Data Prompts for Differential Equation Problems","created":"2023-04-17","cited_by_count":101},{"id":"2310.02994","title":"Multiple Physics Pretraining for Physical Surrogate Models","created":"2023-10-04","cited_by_count":98},{"id":"2204.09810","title":"Deep transfer operator learning for partial differential equations under conditional shift","created":"2022-04-20","cited_by_count":83},{"id":"2309.01745","title":"Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation","created":"2023-09-04","cited_by_count":71},{"id":"2403.05231","title":"Tracking Meets LoRA: Faster Training, Larger Model, Stronger Performance","created":"2024-03-08","cited_by_count":70},{"id":"2109.05237","title":"Physics-based Deep Learning","created":"2021-09-11","cited_by_count":68},{"id":"2407.11046","title":"A Survey on LoRA of Large Language Models","created":"2024-07-08","cited_by_count":67},{"id":"2411.00180","title":"APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs","created":"2024-10-31","cited_by_count":60},{"id":"2203.01360","title":"Neural Galerkin Schemes with Active Learning for High-Dimensional Evolution Equations","created":"2022-03-02","cited_by_count":56},{"id":"2405.02730","title":"U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers","created":"2024-05-04","cited_by_count":54},{"id":"2207.00556","title":"Learning to correct spectral methods for simulating turbulent flows","created":"2022-07-01","cited_by_count":49},{"id":"2304.14118","title":"Learning Neural PDE Solvers with Parameter-Guided Channel Attention","created":"2023-04-27","cited_by_count":38},{"id":"2104.10873","title":"Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains","created":"2021-04-22","cited_by_count":37},{"id":"2501.00365","title":"Low-Rank Adaptation for Foundation Models: A Comprehensive Review","created":"2024-12-31","cited_by_count":37},{"id":"2311.17601","title":"Continual Learning with Low Rank Adaptation","created":"2023-11-29","cited_by_count":29},{"id":"2009.12919","title":"Benchmarking deep inverse models over time, and the neural-adjoint method","created":"2020-09-27","cited_by_count":28},{"id":"2212.04663","title":"Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations","created":"2022-12-09","cited_by_count":28},{"id":"2312.05320","title":"Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models","created":"2023-12-08","cited_by_count":23},{"id":"1807.02901","title":"Quantifying model form uncertainty in Reynolds-averaged turbulence models with Bayesian deep neural networks","created":"2018-07-08","cited_by_count":20},{"id":"2405.10216","title":"Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting","created":"2024-05-16","cited_by_count":18},{"id":"2301.10250","title":"Solving Inverse Physics Problems with Score Matching","created":"2023-01-24","cited_by_count":16},{"id":"2208.03498","title":"Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies","created":"2022-08-06","cited_by_count":11},{"id":"2402.04964","title":"ConvLoRA and AdaBN based Domain Adaptation via Self-Training","created":"2024-02-07","cited_by_count":10},{"id":"2308.06675","title":"Learning fast, accurate, and stable closures of a kinetic theory of an active fluid","created":"2023-08-13","cited_by_count":9},{"id":"2412.20601","title":"MATEY: multiscale adaptive foundation models for spatiotemporal physical systems","created":"2024-12-29","cited_by_count":5},{"id":"2410.10200","title":"Fed-pilot: Optimizing LoRA Allocation for Efficient Federated Fine-Tuning with Heterogeneous Clients","created":"2024-10-14","cited_by_count":3}],"next_cursor":null}