{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1704.01212","title":"Neural Message Passing for Quantum Chemistry","created":"2017-04-04","cited_by_count":3487},{"id":"1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","created":"2013-10-16","cited_by_count":3474},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"1610.02415","title":"Automatic chemical design using a data-driven continuous representation of molecules","created":"2016-10-07","cited_by_count":765},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2108.08877","title":"Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models","created":"2021-08-19","cited_by_count":463},{"id":"1904.01561","title":"Analyzing Learned Molecular Representations for Property Prediction","created":"2019-04-02","cited_by_count":375},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"2102.09548","title":"Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development","created":"2021-02-18","cited_by_count":264},{"id":"2109.06977","title":"Design Guidelines for Prompt Engineering Text-to-Image Generative Models","created":"2021-09-14","cited_by_count":218},{"id":"2106.06130","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","created":"2021-06-11","cited_by_count":204},{"id":"1803.09518","title":"Fr\\'echet ChemNet Distance: A metric for generative models for molecules in drug discovery","created":"2018-03-26","cited_by_count":194},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"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":"2110.04126","title":"3D Infomax improves GNNs for Molecular Property Prediction","created":"2021-10-08","cited_by_count":146},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"1611.03199","title":"Low Data Drug Discovery with One-shot Learning","created":"2016-11-10","cited_by_count":91},{"id":"2110.11316","title":"CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP","created":"2021-10-21","cited_by_count":89},{"id":"2102.07916","title":"Few-Shot Graph Learning for Molecular Property Prediction","created":"2021-02-16","cited_by_count":81},{"id":"1908.05832","title":"Transferable Contrastive Network for Generalized Zero-Shot Learning","created":"2019-08-16","cited_by_count":64},{"id":"2207.06010","title":"Does GNN Pretraining Help Molecular Representation?","created":"2022-07-13","cited_by_count":60},{"id":"1502.02072","title":"Massively Multitask Networks for Drug Discovery","created":"2015-02-06","cited_by_count":49},{"id":"2207.08806","title":"Unified 2D and 3D Pre-Training of Molecular Representations","created":"2022-07-14","cited_by_count":45},{"id":"2107.07994","title":"Property-Aware Relation Networks for Few-Shot Molecular Property Prediction","created":"2021-07-16","cited_by_count":41},{"id":"2109.12575","title":"Paradigm Shift in Natural Language Processing","created":"2021-09-26","cited_by_count":39},{"id":"2005.12964","title":"Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systems","created":"2020-05-20","cited_by_count":38},{"id":"2206.08005","title":"Evaluating Self-Supervised Learning for Molecular Graph Embeddings","created":"2022-06-16","cited_by_count":22},{"id":"2110.05841","title":"Relative Molecule Self-Attention Transformer","created":"2021-10-12","cited_by_count":21},{"id":"2205.02708","title":"Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction","created":"2022-05-05","cited_by_count":21},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18},{"id":"1406.1231","title":"Multi-task Neural Networks for QSAR Predictions","created":"2014-06-04","cited_by_count":17},{"id":"2101.01317","title":"Contrastive Learning for Recommender System","created":"2021-01-05","cited_by_count":16},{"id":"2109.08830","title":"Multilingual Molecular Representation Learning via Contrastive Pre-training","created":"2021-09-18","cited_by_count":12},{"id":"2110.04943","title":"SCEHR: Supervised Contrastive Learning for Clinical Risk Prediction using Electronic Health Records","created":"2021-10-11","cited_by_count":10},{"id":"2003.05996","title":"Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction","created":"2020-03-12","cited_by_count":7},{"id":"2209.15101","title":"Improving Molecular Pretraining with Complementary Featurizations","created":"2022-09-29","cited_by_count":4}],"next_cursor":null}