{"list":"other","total":87,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"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":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"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":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"1703.00564","title":"MoleculeNet: A Benchmark for Molecular Machine Learning","created":"2017-03-02","cited_by_count":1051},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"1707.06209","title":"Crowdsourcing Multiple Choice Science Questions","created":"2017-07-19","cited_by_count":765},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2305.08322","title":"C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models","created":"2023-05-15","cited_by_count":708},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2304.13712","title":"Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond","created":"2023-04-26","cited_by_count":411},{"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":"1811.09621","title":"GuacaMol: Benchmarking Models for De Novo Molecular Design","created":"2018-11-22","cited_by_count":297},{"id":"1811.12823","title":"Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models","created":"2018-11-29","cited_by_count":275},{"id":"2110.07728","title":"Pre-training Molecular Graph Representation with 3D Geometry","created":"2021-10-07","cited_by_count":248},{"id":"2006.05531","title":"GEOM: Energy-annotated molecular conformations for property prediction and molecular generation","created":"2020-06-09","cited_by_count":243},{"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":"2203.15827","title":"LinkBERT: Pretraining Language Models with Document Links","created":"2022-03-29","cited_by_count":211},{"id":"2106.09553","title":"Large-Scale Chemical Language Representations Capture Molecular Structure and Properties","created":"2021-06-17","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":"2212.03551","title":"Talking About Large Language Models","created":"2022-12-07","cited_by_count":175},{"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":"2007.06225","title":"ProtTrans: Towards Cracking the Language of Life's Code Through Self-Supervised Deep Learning and High Performance Computing","created":"2020-07-13","cited_by_count":162},{"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":"2306.08018","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","created":"2023-06-13","cited_by_count":133},{"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":"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":"2308.09442","title":"BioMedGPT: Open Multimodal Generative Pre-trained Transformer for BioMedicine","created":"2023-08-18","cited_by_count":100},{"id":"2310.07276","title":"BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations","created":"2023-10-11","cited_by_count":100},{"id":"2301.12586","title":"Unifying Molecular and Textual Representations via Multi-task Language Modelling","created":"2023-01-29","cited_by_count":93},{"id":"2002.08264","title":"Molecule Attention Transformer","created":"2020-02-19","cited_by_count":92},{"id":"1911.04738","title":"SMILES Transformer: Pre-trained Molecular Fingerprint for Low Data Drug Discovery","created":"2019-11-12","cited_by_count":90},{"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":"2305.10688","title":"MolXPT: Wrapping Molecules with Text for Generative Pre-training","created":"2023-05-18","cited_by_count":81},{"id":"2205.13760","title":"Tranception: protein fitness prediction with autoregressive transformers and inference-time retrieval","created":"2022-05-27","cited_by_count":79},{"id":"2301.12040","title":"ProtST: Multi-Modality Learning of Protein Sequences and Biomedical Texts","created":"2023-01-28","cited_by_count":78},{"id":"2206.02096","title":"PEER: A Comprehensive and Multi-Task Benchmark for Protein Sequence Understanding","created":"2022-06-05","cited_by_count":77},{"id":"2010.06060","title":"BioMegatron: Larger Biomedical Domain Language Model","created":"2020-10-12","cited_by_count":76},{"id":"2012.06051","title":"Mapping the Space of Chemical Reactions Using Attention-Based Neural Networks","created":"2020-12-09","cited_by_count":70},{"id":"2201.11147","title":"OntoProtein: Protein Pretraining With Gene Ontology Embedding","created":"2022-01-23","cited_by_count":70},{"id":"2302.01649","title":"Structure-informed Language Models Are Protein Designers","created":"2023-02-03","cited_by_count":68},{"id":"2203.14500","title":"MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design","created":"2022-03-28","cited_by_count":66},{"id":"2302.04611","title":"A Text-guided Protein Design Framework","created":"2023-02-09","cited_by_count":64},{"id":"2306.05783","title":"Xiezhi: An Ever-Updating Benchmark for Holistic Domain Knowledge Evaluation","created":"2023-06-09","cited_by_count":52},{"id":"2401.06199","title":"xTrimoPGLM: Unified 100B-Scale Pre-trained Transformer for Deciphering the Language of Protein","created":"2024-01-11","cited_by_count":50},{"id":"2303.03363","title":"Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language","created":"2023-03-06","cited_by_count":44},{"id":"2205.05789","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","created":"2022-05-11","cited_by_count":42},{"id":"2309.03907","title":"DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs","created":"2023-05-18","cited_by_count":40},{"id":"2308.13565","title":"DARWIN Series: Domain Specific Large Language Models for Natural Science","created":"2023-08-25","cited_by_count":39},{"id":"2005.02799","title":"An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining","created":"2020-05-06","cited_by_count":35},{"id":"2307.14367","title":"Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers","created":"2023-07-25","cited_by_count":32},{"id":"2305.18090","title":"ChatGPT-powered Conversational Drug Editing Using Retrieval and Domain Feedback","created":"2023-05-29","cited_by_count":31},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28},{"id":"2205.11342","title":"The Diminishing Returns of Masked Language Models to Science","created":"2022-05-23","cited_by_count":22},{"id":"2103.00213","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","created":"2021-02-27","cited_by_count":20},{"id":"2110.15527","title":"Pre-training Co-evolutionary Protein Representation via A Pairwise Masked Language Model","created":"2021-10-29","cited_by_count":20},{"id":"2211.16349","title":"BARTSmiles: Generative Masked Language Models for Molecular Representations","created":"2022-11-29","cited_by_count":18},{"id":"2211.16742","title":"Protein Language Models and Structure Prediction: Connection and Progression","created":"2022-11-30","cited_by_count":17},{"id":"2303.06275","title":"A Systematic Study of Joint Representation Learning on Protein Sequences and Structures","created":"2023-03-11","cited_by_count":15},{"id":"2311.07621","title":"To Transformers and Beyond: Large Language Models for the Genome","created":"2023-11-13","cited_by_count":15},{"id":"2106.08279","title":"First Place Solution of KDD Cup 2021 & OGB Large-Scale Challenge Graph Prediction Track","created":"2021-06-15","cited_by_count":10},{"id":"2209.00981","title":"Exploiting Pretrained Biochemical Language Models for Targeted Drug Design","created":"2022-09-02","cited_by_count":10},{"id":"2310.00115","title":"Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks","created":"2023-09-29","cited_by_count":9},{"id":"2301.02748","title":"Generative Antibody Design for Complementary Chain Pairing Sequences through Encoder-Decoder Language Model","created":"2023-01-06","cited_by_count":5},{"id":"2306.01824","title":"Enhancing the Protein Tertiary Structure Prediction by Multiple Sequence Alignment Generation","created":"2023-06-02","cited_by_count":5},{"id":"2201.06001","title":"GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation","created":"2022-01-16","cited_by_count":4},{"id":"2212.01495","title":"iEnhancer-ELM: improve enhancer identification by extracting position-related multiscale contextual information based on enhancer language models","created":"2022-12-03","cited_by_count":2},{"id":"2311.02333","title":"Understanding the Natural Language of DNA using Encoder-Decoder Foundation Models with Byte-level Precision","created":"2023-11-04","cited_by_count":1}],"next_cursor":null}