{"list":"other","total":62,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1602.07576","title":"Group Equivariant Convolutional Networks","created":"2016-02-24","cited_by_count":1165},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"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":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"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":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"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":"2110.02905","title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","created":"2021-10-06","cited_by_count":228},{"id":"1809.10853","title":"Adaptive Input Representations for Neural Language Modeling","created":"2018-09-28","cited_by_count":226},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1909.02487","title":"Ab-Initio Solution of the Many-Electron Schr\\\"odinger Equation with Deep Neural Networks","created":"2019-09-05","cited_by_count":200},{"id":"1909.08423","title":"Deep neural network solution of the electronic Schr\\\"odinger equation","created":"2019-09-16","cited_by_count":127},{"id":"2210.05274","title":"Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design","created":"2022-10-11","cited_by_count":122},{"id":"2207.10551","title":"Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?","created":"2022-07-21","cited_by_count":103},{"id":"2312.03687","title":"MatterGen: a generative model for inorganic materials design","created":"2023-12-06","cited_by_count":98},{"id":"1804.03393","title":"Roto-Translation Covariant Convolutional Networks for Medical Image Analysis","created":"2018-04-10","cited_by_count":92},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2008.05456","title":"Sampling using $SU(N)$ gauge equivariant flows","created":"2020-08-12","cited_by_count":84},{"id":"2203.04439","title":"$\\mathrm{SO}(2)$-Equivariant Reinforcement Learning","created":"2022-03-08","cited_by_count":84},{"id":"2005.00178","title":"On the Benefits of Invariance in Neural Networks","created":"2020-05-01","cited_by_count":79},{"id":"2104.03113","title":"Scaling Scaling Laws with Board Games","created":"2021-04-07","cited_by_count":63},{"id":"2110.15443","title":"Equivariant $Q$ Learning in Spatial Action Spaces","created":"2021-10-28","cited_by_count":62},{"id":"2305.11141","title":"Clifford Group Equivariant Neural Networks","created":"2023-05-18","cited_by_count":55},{"id":"2305.18415","title":"Geometric Algebra Transformer","created":"2023-05-28","cited_by_count":48},{"id":"2305.17592","title":"Approximation-Generalization Trade-offs under (Approximate) Group Equivariance","created":"2023-05-27","cited_by_count":46},{"id":"2212.03574","title":"Learning rigid dynamics with face interaction graph networks","created":"2022-12-07","cited_by_count":43},{"id":"1610.04574","title":"Generalization Error of Invariant Classifiers","created":"2016-10-14","cited_by_count":42},{"id":"2203.04923","title":"On-Robot Learning With Equivariant Models","created":"2022-03-09","cited_by_count":42},{"id":"2009.11193","title":"ContactNets: Learning Discontinuous Contact Dynamics with Smooth, Implicit Representations","created":"2020-09-23","cited_by_count":38},{"id":"2302.06594","title":"Geometric Clifford Algebra Networks","created":"2023-02-13","cited_by_count":38},{"id":"2405.14806","title":"Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics","created":"2024-05-23","cited_by_count":38},{"id":"2207.00283","title":"Learning Lattice Quantum Field Theories with Equivariant Continuous Flows","created":"2022-07-01","cited_by_count":37},{"id":"1804.04656","title":"3D G-CNNs for Pulmonary Nodule Detection","created":"2018-04-12","cited_by_count":36},{"id":"2303.12410","title":"EDGI: Equivariant Diffusion for Planning with Embodied Agents","created":"2023-03-22","cited_by_count":36},{"id":"1910.06552","title":"Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces","created":"2019-10-15","cited_by_count":34},{"id":"2212.05023","title":"Mesh Neural Networks for SE(3)-Equivariant Hemodynamics Estimation on the Artery Wall","created":"2022-12-09","cited_by_count":29},{"id":"2406.06248","title":"Compute Better Spent: Replacing Dense Layers with Structured Matrices","created":"2024-06-10","cited_by_count":28},{"id":"2211.00454","title":"PELICAN: Permutation Equivariant and Lorentz Invariant or Covariant Aggregator Network for Particle Physics","created":"2022-11-01","cited_by_count":26},{"id":"2402.14730","title":"Clifford-Steerable Convolutional Neural Networks","created":"2024-02-22","cited_by_count":25},{"id":"2402.10011","title":"Clifford Group Equivariant Simplicial Message Passing Networks","created":"2024-02-15","cited_by_count":22},{"id":"2210.13150","title":"A PAC-Bayesian Generalization Bound for Equivariant Networks","created":"2022-10-24","cited_by_count":18},{"id":"2311.04744","title":"Euclidean, Projective, Conformal: Choosing a Geometric Algebra for Equivariant Transformers","created":"2023-11-08","cited_by_count":13},{"id":"2405.14045","title":"Learning rigid-body simulators over implicit shapes for large-scale scenes and vision","created":"2024-05-22","cited_by_count":12},{"id":"2004.09691","title":"A Data and Compute Efficient Design for Limited-Resources Deep Learning","created":"2020-04-21","cited_by_count":10},{"id":"1704.03033","title":"A probabilistic data-driven model for planar pushing","created":"2017-04-10","cited_by_count":9},{"id":"2406.14995","title":"Differentiable and Learnable Wireless Simulation with Geometric Transformers","created":"2024-06-21","cited_by_count":6},{"id":"2406.04052","title":"Multivector Neurons: Better and Faster O(n)-Equivariant Clifford Graph Neural Networks","created":"2024-06-06","cited_by_count":5},{"id":"2406.01630","title":"Equivariant amortized inference of poses for cryo-EM","created":"2024-06-01","cited_by_count":1}],"next_cursor":null}