{"list":"other","total":59,"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":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"1903.02428","title":"Fast Graph Representation Learning with PyTorch Geometric","created":"2019-03-06","cited_by_count":2434},{"id":"1801.07829","title":"Dynamic Graph CNN for Learning on Point Clouds","created":"2018-01-24","cited_by_count":2223},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2102.09844","title":"E(n) Equivariant Graph Neural Networks","created":"2021-02-19","cited_by_count":965},{"id":"1511.05493","title":"Gated Graph Sequence Neural Networks","created":"2015-11-17","cited_by_count":796},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","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":"2002.11296","title":"Sparse Sinkhorn Attention","created":"2020-02-26","cited_by_count":251},{"id":"2109.02497","title":"Voxel Transformer for 3D Object Detection","created":"2021-09-06","cited_by_count":247},{"id":"2306.08385","title":"NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification","created":"2023-06-14","cited_by_count":210},{"id":"2107.14222","title":"Rethinking and Improving Relative Position Encoding for Vision Transformer","created":"2021-07-29","cited_by_count":207},{"id":"2112.06375","title":"Embracing Single Stride 3D Object Detector with Sparse Transformer","created":"2021-12-13","cited_by_count":193},{"id":"2303.06147","title":"Exphormer: Sparse Transformers for Graphs","created":"2023-03-10","cited_by_count":170},{"id":"2202.05146","title":"EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction","created":"2022-02-07","cited_by_count":144},{"id":"2206.04910","title":"NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs","created":"2022-06-10","cited_by_count":137},{"id":"2110.15343","title":"Scatterbrain: Unifying Sparse and Low-rank Attention Approximation","created":"2021-10-28","cited_by_count":130},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122},{"id":"1405.5869","title":"Asymmetric LSH (ALSH) for Sublinear Time Maximum Inner Product Search (MIPS)","created":"2014-05-22","cited_by_count":109},{"id":"1509.02897","title":"Practical and Optimal LSH for Angular Distance","created":"2015-09-09","cited_by_count":106},{"id":"2202.03772","title":"Particle Transformer for Jet Tagging","created":"2022-02-08","cited_by_count":98},{"id":"2210.07372","title":"SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds","created":"2022-10-13","cited_by_count":92},{"id":"2310.05869","title":"HyperAttention: Long-context Attention in Near-Linear Time","created":"2023-10-09","cited_by_count":85},{"id":"2010.00130","title":"Computing Graph Neural Networks: A Survey from Algorithms to Accelerators","created":"2020-09-30","cited_by_count":81},{"id":"1506.02785","title":"On the Error of Random Fourier Features","created":"2015-06-09","cited_by_count":76},{"id":"2301.08739","title":"FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer","created":"2023-01-20","cited_by_count":73},{"id":"2210.03930","title":"Hierarchical Graph Transformer with Adaptive Node Sampling","created":"2022-10-08","cited_by_count":72},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51},{"id":"2106.11535","title":"Particle Cloud Generation with Message Passing Generative Adversarial Networks","created":"2021-06-22","cited_by_count":46},{"id":"1902.07987","title":"Learning representations of irregular particle-detector geometry with distance-weighted graph networks","created":"2019-02-21","cited_by_count":43},{"id":"2010.05315","title":"SMYRF: Efficient Attention using Asymmetric Clustering","created":"2020-10-11","cited_by_count":43},{"id":"2211.10295","title":"Evaluating generative models in high energy physics","created":"2022-11-18","cited_by_count":31},{"id":"1803.02329","title":"Learning Memory Access Patterns","created":"2018-03-06","cited_by_count":28},{"id":"2103.16701","title":"Charged particle tracking via edge-classifying interaction networks","created":"2021-03-30","cited_by_count":19},{"id":"2105.01160","title":"The Tracking Machine Learning challenge : Throughput phase","created":"2021-05-03","cited_by_count":12},{"id":"2203.12852","title":"Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challenges","created":"2022-03-23","cited_by_count":12},{"id":"2302.01925","title":"Learning a Fourier Transform for Linear Relative Positional Encodings in Transformers","created":"2023-02-03","cited_by_count":10},{"id":"1702.05911","title":"Efficient Large-scale Approximate Nearest Neighbor Search on the GPU","created":"2017-02-20","cited_by_count":8},{"id":"2209.03042","title":"Graph Neural Networks for Low-Energy Event Classification & Reconstruction in IceCube","created":"2022-09-07","cited_by_count":8},{"id":"2312.03823","title":"High Pileup Particle Tracking with Object Condensation","created":"2023-12-06","cited_by_count":8},{"id":"2311.03094","title":"Equivariance Is Not All You Need: Characterizing the Utility of Equivariant Graph Neural Networks for Particle Physics Tasks","created":"2023-11-06","cited_by_count":5}],"next_cursor":null}