{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"2002.09405","title":"Learning to Simulate Complex Physics with Graph Networks","created":"2020-02-21","cited_by_count":880},{"id":"1802.08219","title":"Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds","created":"2018-02-22","cited_by_count":746},{"id":"2101.03164","title":"E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials","created":"2021-01-08","cited_by_count":708},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2006.10503","title":"SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks","created":"2020-06-18","cited_by_count":607},{"id":"1706.08566","title":"SchNet: A continuous-filter convolutional neural network for modeling quantum interactions","created":"2017-06-26","cited_by_count":571},{"id":"2003.03123","title":"Directional Message Passing for Molecular Graphs","created":"2020-03-06","cited_by_count":561},{"id":"2206.07697","title":"MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields","created":"2022-06-15","cited_by_count":474},{"id":"1801.10130","title":"Spherical CNNs","created":"2018-01-30","cited_by_count":456},{"id":"2102.03150","title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","created":"2021-02-05","cited_by_count":441},{"id":"1807.02547","title":"3D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Data","created":"2018-07-06","cited_by_count":354},{"id":"2009.01411","title":"Learning from Protein Structure with Geometric Vector Perceptrons","created":"2020-09-03","cited_by_count":313},{"id":"2205.05131","title":"UL2: Unifying Language Learning Paradigms","created":"2022-05-10","cited_by_count":295},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264},{"id":"2204.05249","title":"Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics","created":"2022-04-11","cited_by_count":256},{"id":"2010.09990","title":"The Open Catalyst 2020 (OC20) Dataset and Community Challenges","created":"2020-10-20","cited_by_count":246},{"id":"2110.02905","title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","created":"2021-10-06","cited_by_count":228},{"id":"1707.09571","title":"Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics","created":"2017-07-30","cited_by_count":214},{"id":"2306.12059","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","created":"2023-06-21","cited_by_count":204},{"id":"2202.02541","title":"TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials","created":"2022-02-05","cited_by_count":182},{"id":"2207.09453","title":"e3nn: Euclidean Neural Networks","created":"2022-07-18","cited_by_count":174},{"id":"1806.09231","title":"Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Network","created":"2018-06-24","cited_by_count":171},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124},{"id":"2302.03655","title":"Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs","created":"2023-02-07","cited_by_count":117},{"id":"1807.07814","title":"Interactive Supercomputing on 40,000 Cores for Machine Learning and Data Analysis","created":"2018-07-20","cited_by_count":110},{"id":"2206.08917","title":"The Open Catalyst 2022 (OC22) Dataset and Challenges for Oxide Electrocatalysts","created":"2022-06-17","cited_by_count":95},{"id":"2210.07237","title":"Forces are not Enough: Benchmark and Critical Evaluation for Machine Learning Force Fields with Molecular Simulations","created":"2022-10-13","cited_by_count":95},{"id":"1801.09319","title":"Less is more: sampling chemical space with active learning","created":"2018-01-28","cited_by_count":82},{"id":"2305.05577","title":"FAENet: Frame Averaging Equivariant GNN for Materials Modeling","created":"2023-04-28","cited_by_count":73},{"id":"2206.13602","title":"Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching","created":"2022-06-27","cited_by_count":68},{"id":"2312.07511","title":"A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems","created":"2023-12-12","cited_by_count":68},{"id":"2106.02347","title":"SE(3)-equivariant prediction of molecular wavefunctions and electronic densities","created":"2021-06-04","cited_by_count":67},{"id":"2204.02782","title":"GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets","created":"2022-04-06","cited_by_count":61},{"id":"2008.08461","title":"Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties","created":"2020-08-19","cited_by_count":51},{"id":"2206.14331","title":"Spherical Channels for Modeling Atomic Interactions","created":"2022-06-29","cited_by_count":47},{"id":"2207.08824","title":"Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs","created":"2022-07-18","cited_by_count":37},{"id":"2304.10061","title":"Scaling the leading accuracy of deep equivariant models to biomolecular simulations of realistic size","created":"2023-04-20","cited_by_count":33},{"id":"2307.10683","title":"Fractional Denoising for 3D Molecular Pre-training","created":"2023-07-20","cited_by_count":33},{"id":"2202.09891","title":"Equivariant Graph Attention Networks for Molecular Property Prediction","created":"2022-02-20","cited_by_count":20},{"id":"2308.14759","title":"May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations","created":"2023-08-24","cited_by_count":13},{"id":"2303.02216","title":"Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials","created":"2023-03-03","cited_by_count":11},{"id":"2006.14163","title":"Geometric Prediction: Moving Beyond Scalars","created":"2020-06-25","cited_by_count":10},{"id":"1708.04987","title":"ANI-1: A data set of 20M off-equilibrium DFT calculations for organic molecules","created":"2017-08-16","cited_by_count":1}],"next_cursor":null}