{"list":"other","total":105,"rows":[{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2305.14314","title":"QLoRA: Efficient Finetuning of Quantized LLMs","created":"2023-05-23","cited_by_count":3418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"1906.08237","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","created":"2019-06-19","cited_by_count":2811},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"1903.10676","title":"SciBERT: A Pretrained Language Model for Scientific Text","created":"2019-03-26","cited_by_count":1414},{"id":"2103.10360","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling","created":"2021-03-18","cited_by_count":1031},{"id":"2007.15779","title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","created":"2020-07-31","cited_by_count":1009},{"id":"2211.09085","title":"Galactica: A Large Language Model for Science","created":"2022-11-16","cited_by_count":744},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2009.01411","title":"Learning from Protein Structure with Geometric Vector Perceptrons","created":"2020-09-03","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":"1906.08230","title":"Evaluating Protein Transfer Learning with TAPE","created":"2019-06-19","cited_by_count":231},{"id":"2307.02046","title":"Recommender Systems in the Era of Large Language Models (LLMs)","created":"2023-07-05","cited_by_count":189},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177},{"id":"2310.05694","title":"A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics","created":"2023-10-09","cited_by_count":163},{"id":"2203.06125","title":"Protein Representation Learning by Geometric Structure Pretraining","created":"2022-03-11","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":"2306.08018","title":"Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models","created":"2023-06-13","cited_by_count":133},{"id":"2209.01712","title":"ChemBERTa-2: Towards Chemical Foundation Models","created":"2022-09-05","cited_by_count":127},{"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":"2402.18567","title":"Diffusion Language Models Are Versatile Protein Learners","created":"2024-02-28","cited_by_count":98},{"id":"2306.06615","title":"Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective","created":"2023-06-11","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":"2209.12643","title":"PiFold: Toward effective and efficient protein inverse folding","created":"2022-09-22","cited_by_count":83},{"id":"2302.02591","title":"Generative Diffusion Models on Graphs: Methods and Applications","created":"2023-02-06","cited_by_count":81},{"id":"2401.14656","title":"Scientific Large Language Models: A Survey on Biological & Chemical Domains","created":"2024-01-26","cited_by_count":80},{"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":"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":"2412.12101","title":"InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders","created":"2024-11-13","cited_by_count":66},{"id":"2302.04611","title":"A Text-guided Protein Design Framework","created":"2023-02-09","cited_by_count":64},{"id":"2402.04268","title":"ProtAgents: Protein discovery via large language model multi-agent collaborations combining physics and machine learning","created":"2024-01-27","cited_by_count":64},{"id":"2410.13782","title":"DPLM-2: A Multimodal Diffusion Protein Language Model","created":"2024-10-17","cited_by_count":64},{"id":"2402.17810","title":"BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning","created":"2024-02-27","cited_by_count":54},{"id":"2112.07782","title":"Deciphering antibody affinity maturation with language models and weakly supervised learning","created":"2021-12-14","cited_by_count":53},{"id":"2402.16445","title":"ProLLaMA: A Protein Large Language Model for Multi-Task Protein Language Processing","created":"2024-02-26","cited_by_count":53},{"id":"2202.01338","title":"Regression Transformer: Concurrent sequence regression and generation for molecular language modeling","created":"2022-02-01","cited_by_count":50},{"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":"1706.01010","title":"DeepSF: deep convolutional neural network for mapping protein sequences to folds","created":"2017-06-04","cited_by_count":46},{"id":"2301.06568","title":"Ankh: Optimized Protein Language Model Unlocks General-Purpose Modelling","created":"2023-01-16","cited_by_count":45},{"id":"2205.05789","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","created":"2022-05-11","cited_by_count":42},{"id":"2408.01129","title":"A Survey of Mamba","created":"2024-08-02","cited_by_count":39},{"id":"2406.10450","title":"TokenRec: Learning to Tokenize ID for LLM-based Generative Recommendation","created":"2024-06-15","cited_by_count":35},{"id":"2404.14928","title":"Graph Machine Learning in the Era of Large Language Models (LLMs)","created":"2024-04-23","cited_by_count":33},{"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":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29},{"id":"2310.03269","title":"InstructProtein: Aligning Human and Protein Language via Knowledge Instruction","created":"2023-10-05","cited_by_count":28},{"id":"2405.12564","title":"ProtT3: Protein-to-Text Generation for Text-based Protein Understanding","created":"2024-05-21","cited_by_count":25},{"id":"2406.12950","title":"MolecularGPT: Open Large Language Model (LLM) for Few-Shot Molecular Property Prediction","created":"2024-06-18","cited_by_count":24},{"id":"2408.11363","title":"ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding","created":"2024-08-21","cited_by_count":23},{"id":"2309.03099","title":"PeptideBERT: A Language Model based on Transformers for Peptide Property Prediction","created":"2023-08-28","cited_by_count":21},{"id":"2403.07920","title":"ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training","created":"2024-02-28","cited_by_count":21},{"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":"2210.07144","title":"Reprogramming Pretrained Language Models for Antibody Sequence Infilling","created":"2022-10-05","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":"2402.09649","title":"ProtChatGPT: Towards Understanding Proteins with Large Language Models","created":"2024-02-15","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":"2403.01528","title":"Leveraging Biomolecule and Natural Language through Multi-Modal Learning: A Survey","created":"2024-03-03","cited_by_count":17},{"id":"2403.17889","title":"Large scale paired antibody language models","created":"2024-03-26","cited_by_count":16},{"id":"2207.13921","title":"HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative","created":"2022-07-28","cited_by_count":15},{"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":"2109.13187","title":"Discovering Drug-Target Interaction Knowledge from Biomedical Literature","created":"2021-09-27","cited_by_count":14},{"id":"2408.13659","title":"ReactZyme: A Benchmark for Enzyme-Reaction Prediction","created":"2024-08-24","cited_by_count":13},{"id":"2405.06649","title":"ProLLM: Protein Chain-of-Thoughts Enhanced LLM for Protein-Protein Interaction Prediction","created":"2024-03-30","cited_by_count":12},{"id":"2411.02142","title":"Training Compute-Optimal Protein Language Models","created":"2024-11-04","cited_by_count":12},{"id":"2401.14819","title":"Endowing Protein Language Models with Structural Knowledge","created":"2024-01-26","cited_by_count":11},{"id":"2301.00813","title":"A Survey on Protein Representation Learning: Retrospect and Prospect","created":"2022-12-31","cited_by_count":10},{"id":"2410.07919","title":"Advancing biomolecular understanding and design following human instructions","created":"2024-10-10","cited_by_count":10},{"id":"2204.07110","title":"Generative power of a protein language model trained on multiple sequence alignments","created":"2022-04-14","cited_by_count":9},{"id":"2401.04374","title":"Towards Explainable Artificial Intelligence (XAI): A Data Mining Perspective","created":"2024-01-09","cited_by_count":9},{"id":"2409.01192","title":"SSD4Rec: A Structured State Space Duality Model for Efficient Sequential Recommendation","created":"2024-09-02","cited_by_count":9},{"id":"2308.05326","title":"OpenProteinSet: Training data for structural biology at scale","created":"2023-08-10","cited_by_count":8},{"id":"2406.05347","title":"MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training","created":"2024-06-08","cited_by_count":7},{"id":"2402.05856","title":"Structure-Informed Protein Language Model","created":"2024-02-07","cited_by_count":6},{"id":"2407.19296","title":"Multi-Modal CLIP-Informed Protein Editing","created":"2024-07-27","cited_by_count":6},{"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}],"next_cursor":"100"}