{"list":"other","total":86,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139},{"id":"2202.03629","title":"Survey of Hallucination in Natural Language Generation","created":"2022-02-08","cited_by_count":2075},{"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":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"1405.4053","title":"Distributed Representations of Sentences and Documents","created":"2014-05-16","cited_by_count":678},{"id":"2306.08302","title":"Unifying Large Language Models and Knowledge Graphs: A Roadmap","created":"2023-06-14","cited_by_count":668},{"id":"2210.10341","title":"BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining","created":"2022-10-19","cited_by_count":538},{"id":"2305.18654","title":"Faith and Fate: Limits of Transformers on Compositionality","created":"2023-05-29","cited_by_count":503},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1904.05342","title":"ClinicalBERT: Modeling Clinical Notes and Predicting Hospital Readmission","created":"2019-04-10","cited_by_count":493},{"id":"2311.17035","title":"Scalable Extraction of Training Data from (Production) Language Models","created":"2023-11-28","cited_by_count":434},{"id":"1608.05745","title":"RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism","created":"2016-08-19","cited_by_count":349},{"id":"2308.03296","title":"Studying Large Language Model Generalization with Influence Functions","created":"2023-08-07","cited_by_count":326},{"id":"2210.01776","title":"DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking","created":"2022-10-04","cited_by_count":313},{"id":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289},{"id":"2301.13867","title":"Mathematical Capabilities of ChatGPT","created":"2023-01-31","cited_by_count":268},{"id":"1704.07555","title":"Molecular De Novo Design through Deep Reinforcement Learning","created":"2017-04-25","cited_by_count":267},{"id":"1906.08230","title":"Evaluating Protein Transfer Learning with TAPE","created":"2019-06-19","cited_by_count":231},{"id":"1811.02633","title":"Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction","created":"2018-11-06","cited_by_count":229},{"id":"2106.09553","title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","created":"2021-06-17","cited_by_count":206},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","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":"2206.13517","title":"ProGen2: Exploring the Boundaries of Protein Language Models","created":"2022-06-27","cited_by_count":159},{"id":"2306.15006","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","created":"2023-06-26","cited_by_count":143},{"id":"1801.04334","title":"TieNet: Text-Image Embedding Network for Common Thorax Disease Classification and Reporting in Chest X-rays","created":"2018-01-12","cited_by_count":139},{"id":"1904.02633","title":"Clinically Accurate Chest X-Ray Report Generation","created":"2019-04-04","cited_by_count":139},{"id":"2209.05481","title":"A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language","created":"2022-09-12","cited_by_count":131},{"id":"2004.03497","title":"ProGen: Language Modeling for Protein Generation","created":"2020-03-08","cited_by_count":128},{"id":"1705.10843","title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models","created":"2017-05-30","cited_by_count":117},{"id":"1706.05764","title":"Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks","created":"2017-06-19","cited_by_count":116},{"id":"2311.07361","title":"The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4","created":"2023-11-13","cited_by_count":112},{"id":"2310.10196","title":"Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlook","created":"2023-10-16","cited_by_count":110},{"id":"2212.14882","title":"ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports","created":"2022-12-30","cited_by_count":101},{"id":"2105.11333","title":"Multi-modal Understanding and Generation for Medical Images and Text via Vision-Language Pre-Training","created":"2021-05-24","cited_by_count":96},{"id":"2103.13136","title":"Representing Numbers in NLP: a Survey and a Vision","created":"2021-03-24","cited_by_count":83},{"id":"2308.06911","title":"GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text","created":"2023-08-14","cited_by_count":82},{"id":"2207.00939","title":"An Empirical Survey on Long Document Summarization: Datasets, Models and Metrics","created":"2022-07-03","cited_by_count":74},{"id":"2307.15051","title":"Matching Patients to Clinical Trials with Large Language Models","created":"2023-07-27","cited_by_count":69},{"id":"2112.03041","title":"Keeping it Simple: Language Models can learn Complex Molecular Distributions","created":"2021-12-06","cited_by_count":68},{"id":"2302.04611","title":"A Text-guided Protein Design Framework","created":"2023-02-09","cited_by_count":64},{"id":"2102.04252","title":"HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data","created":"2021-02-08","cited_by_count":49},{"id":"2207.05289","title":"PLM-ICD: Automatic ICD Coding with Pretrained Language Models","created":"2022-07-12","cited_by_count":49},{"id":"2001.10054","title":"StageNet: Stage-Aware Neural Networks for Health Risk Prediction","created":"2020-01-24","cited_by_count":48},{"id":"1807.08820","title":"RAIM: Recurrent Attentive and Intensive Model of Multimodal Patient Monitoring Data","created":"2018-07-23","cited_by_count":47},{"id":"2205.05789","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","created":"2022-05-11","cited_by_count":42},{"id":"2310.07984","title":"Large Language Models for Scientific Synthesis, Inference and Explanation","created":"2023-10-12","cited_by_count":39},{"id":"2006.03685","title":"BERT-XML: Large Scale Automated ICD Coding Using BERT Pretraining","created":"2020-05-26","cited_by_count":37},{"id":"2006.08765","title":"COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching","created":"2020-06-15","cited_by_count":37},{"id":"1711.04075","title":"Towards Automated ICD Coding Using Deep Learning","created":"2017-11-11","cited_by_count":35},{"id":"2305.18090","title":"ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback","created":"2023-05-29","cited_by_count":31},{"id":"2310.02989","title":"xVal: A Continuous Numerical Tokenization for Scientific Language Models","created":"2023-10-04","cited_by_count":27},{"id":"2210.16732","title":"How Far are We from Robust Long Abstractive Summarization?","created":"2022-10-30","cited_by_count":25},{"id":"2304.03889","title":"DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models","created":"2023-04-08","cited_by_count":24},{"id":"2305.12081","title":"MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement","created":"2023-05-20","cited_by_count":24},{"id":"2206.06583","title":"Exploring evolution-aware & -free protein language models as protein function predictors","created":"2022-06-14","cited_by_count":20},{"id":"2104.13498","title":"Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes","created":"2021-04-27","cited_by_count":19},{"id":"2206.14719","title":"Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision","created":"2022-06-29","cited_by_count":18},{"id":"2303.07735","title":"Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models","created":"2023-03-14","cited_by_count":18},{"id":"2108.10307","title":"C5T5: Controllable Generation of Organic Molecules with Transformers","created":"2021-08-23","cited_by_count":16},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15},{"id":"2304.05352","title":"SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning","created":"2023-04-07","cited_by_count":13},{"id":"2307.14522","title":"CliniDigest: A Case Study in Large Language Model Based Large-Scale Summarization of Clinical Trial Descriptions","created":"2023-07-26","cited_by_count":10},{"id":"2304.07396","title":"Improving Patient Pre-screening for Clinical Trials: Assisting Physicians with Large Language Models","created":"2023-04-14","cited_by_count":6},{"id":"2305.19407","title":"FRAMM: Fair Ranking with Missing Modalities for Clinical Trial Site Selection","created":"2023-05-30","cited_by_count":6},{"id":"2204.01168","title":"Few Shot Protein Generation","created":"2022-04-03","cited_by_count":4},{"id":"2204.06501","title":"Clinical trial site matching with improved diversity using fair policy learning","created":"2022-04-13","cited_by_count":3},{"id":"2312.03016","title":"Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence","created":"2023-12-05","cited_by_count":3}],"next_cursor":null}