{"list":"other","total":57,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1810.00826","title":"How Powerful are Graph Neural Networks?","created":"2018-10-01","cited_by_count":4393},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2107.03006","title":"Structured Denoising Diffusion Models in Discrete State-Spaces","created":"2021-07-07","cited_by_count":1719},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2010.13902","title":"Graph Contrastive Learning with Augmentations","created":"2020-10-22","cited_by_count":1208},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1905.12265","title":"Strategies for Pre-training Graph Neural Networks","created":"2019-05-29","cited_by_count":971},{"id":"2205.12454","title":"Recipe for a General, Powerful, Scalable Graph Transformer","created":"2022-05-25","cited_by_count":713},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2003.03123","title":"Directional Message Passing for Molecular Graphs","created":"2020-03-06","cited_by_count":561},{"id":"2205.10803","title":"GraphMAE: Self-Supervised Masked Graph Autoencoders","created":"2022-05-22","cited_by_count":448},{"id":"1908.01000","title":"InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization","created":"2019-07-31","cited_by_count":441},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1904.01561","title":"Analyzing Learned Molecular Representations for Property Prediction","created":"2019-04-02","cited_by_count":375},{"id":"2010.09885","title":"ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction","created":"2020-10-19","cited_by_count":337},{"id":"2103.09430","title":"OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs","created":"2021-03-17","cited_by_count":329},{"id":"2210.01776","title":"DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking","created":"2022-10-04","cited_by_count":313},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180},{"id":"1801.10193","title":"DeepDTA: Deep Drug-Target Binding Affinity Prediction","created":"2018-01-30","cited_by_count":173},{"id":"2212.10789","title":"Multi-modal Molecule Structure-text Model for Text-based Retrieval and Editing","created":"2022-12-21","cited_by_count":166},{"id":"2203.06125","title":"Protein Representation Learning by Geometric Structure Pretraining","created":"2022-03-11","cited_by_count":162},{"id":"2203.10446","title":"A 3D Generative Model for Structure-Based Drug Design","created":"2022-03-20","cited_by_count":149},{"id":"2110.04126","title":"3D Infomax improves GNNs for Molecular Property Prediction","created":"2021-10-08","cited_by_count":146},{"id":"2206.00133","title":"Pre-training via Denoising for Molecular Property Prediction","created":"2022-05-31","cited_by_count":124},{"id":"2107.12375","title":"Geometric Deep Learning on Molecular Representations","created":"2021-07-26","cited_by_count":113},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78},{"id":"2210.01765","title":"One Transformer Can Understand Both 2D & 3D Molecular Data","created":"2022-10-04","cited_by_count":77},{"id":"2302.01649","title":"Structure-informed Language Models Are Protein Designers","created":"2023-02-03","cited_by_count":68},{"id":"2203.04810","title":"Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets","created":"2022-03-09","cited_by_count":64},{"id":"2107.10670","title":"Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity","created":"2021-07-21","cited_by_count":60},{"id":"1612.02751","title":"Protein-Ligand Scoring with Convolutional Neural Networks","created":"2016-12-08","cited_by_count":57},{"id":"1712.07042","title":"Development and evaluation of a deep learning model for protein-ligand binding affinity prediction","created":"2017-12-19","cited_by_count":51},{"id":"2307.10683","title":"Fractional Denoising for 3D Molecular Pre-training","created":"2023-07-20","cited_by_count":33},{"id":"2305.18407","title":"A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining","created":"2023-05-28","cited_by_count":32},{"id":"2310.06367","title":"DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening","created":"2023-10-10","cited_by_count":28},{"id":"2306.07812","title":"Automated 3D Pre-Training for Molecular Property Prediction","created":"2023-06-13","cited_by_count":24},{"id":"2411.02120","title":"Bridge-IF: Learning Inverse Protein Folding with Markov Bridges","created":"2024-11-04","cited_by_count":9},{"id":"2402.10516","title":"Generative AI for Controllable Protein Sequence Design: A Survey","created":"2024-02-16","cited_by_count":8},{"id":"2306.04886","title":"Multi-task Bioassay Pre-training for Protein-ligand Binding Affinity Prediction","created":"2023-06-08","cited_by_count":7},{"id":"2407.19296","title":"Multi-Modal CLIP-Informed Protein Editing","created":"2024-07-27","cited_by_count":6}],"next_cursor":null}