{"list":"other","total":129,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"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":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2305.18290","title":"Direct Preference Optimization: Your Language Model is Secretly a Reward Model","created":"2023-05-29","cited_by_count":8065},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1508.07909","title":"Neural Machine Translation of Rare Words with Subword Units","created":"2015-08-31","cited_by_count":2918},{"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":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"2009.13081","title":"What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams","created":"2020-09-28","cited_by_count":1356},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"1907.10529","title":"SpanBERT: Improving Pre-training by Representing and Predicting Spans","created":"2019-07-24","cited_by_count":834},{"id":"2305.02301","title":"Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes","created":"2023-05-03","cited_by_count":737},{"id":"1804.10959","title":"Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates","created":"2018-04-29","cited_by_count":639},{"id":"2304.05376","title":"ChemCrow: Augmenting large-language models with chemistry tools","created":"2023-04-11","cited_by_count":631},{"id":"1901.07042","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","created":"2019-01-21","cited_by_count":597},{"id":"2203.14371","title":"MedMCQA : A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","created":"2022-03-27","cited_by_count":543},{"id":"1904.05046","title":"Generalizing from a Few Examples: A Survey on Few-Shot Learning","created":"2019-04-10","cited_by_count":463},{"id":"2302.10866","title":"Hyena Hierarchy: Towards Larger Convolutional Language Models","created":"2023-02-21","cited_by_count":393},{"id":"2106.07139","title":"Pre-Trained Models: Past, Present and Future","created":"2021-06-14","cited_by_count":319},{"id":"1703.03130","title":"A Structured Self-attentive Sentence Embedding","created":"2017-03-09","cited_by_count":318},{"id":"2401.05561","title":"TrustLLM: Trustworthiness in Large Language Models","created":"2024-01-10","cited_by_count":285},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2307.10169","title":"Challenges and Applications of Large Language Models","created":"2023-07-19","cited_by_count":254},{"id":"2309.07430","title":"Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization","created":"2023-09-14","cited_by_count":246},{"id":"2312.07843","title":"Foundation Models in Robotics: Applications, Challenges, and the Future","created":"2023-12-13","cited_by_count":216},{"id":"2305.15075","title":"HuatuoGPT, towards Taming Language Model to Be a Doctor","created":"2023-05-24","cited_by_count":214},{"id":"2305.17100","title":"BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks","created":"2023-05-26","cited_by_count":201},{"id":"2306.15794","title":"HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution","created":"2023-06-27","cited_by_count":194},{"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":"2011.08641","title":"A Review of Generalized Zero-Shot Learning Methods","created":"2020-11-17","cited_by_count":159},{"id":"2106.03164","title":"On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation","created":"2021-06-06","cited_by_count":147},{"id":"2402.01364","title":"Continual Learning for Large Language Models: A Survey","created":"2024-02-02","cited_by_count":147},{"id":"2306.15006","title":"DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genome","created":"2023-06-26","cited_by_count":143},{"id":"2004.03497","title":"ProGen: Language Modeling for Protein Generation","created":"2020-03-08","cited_by_count":128},{"id":"2402.06954","title":"OpenFedLLM: Training Large Language Models on Decentralized Private Data via Federated Learning","created":"2024-02-10","cited_by_count":128},{"id":"2409.18486","title":"Evaluation of OpenAI o1: Opportunities and Challenges of AGI","created":"2024-09-27","cited_by_count":127},{"id":"2306.10070","title":"Opportunities and Challenges for ChatGPT and Large Language Models in Biomedicine and Health","created":"2023-06-15","cited_by_count":118},{"id":"2403.05156","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","created":"2024-03-08","cited_by_count":96},{"id":"2401.04334","title":"Large Language Models for Robotics: Opportunities, Challenges, and Perspectives","created":"2024-01-09","cited_by_count":89},{"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":"2402.06627","title":"Feedback Loops With Language Models Drive In-Context Reward Hacking","created":"2024-02-09","cited_by_count":77},{"id":"2302.01649","title":"Structure-informed Language Models Are Protein Designers","created":"2023-02-03","cited_by_count":68},{"id":"2304.02198","title":"EigenFold: Generative Protein Structure Prediction with Diffusion Models","created":"2023-04-05","cited_by_count":63},{"id":"2401.02038","title":"Understanding LLMs: A Comprehensive Overview from Training to Inference","created":"2024-01-04","cited_by_count":59},{"id":"2304.08448","title":"An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT","created":"2023-04-17","cited_by_count":57},{"id":"2408.01319","title":"A Comprehensive Review of Multimodal Large Language Models: Performance and Challenges Across Different Tasks","created":"2024-08-02","cited_by_count":57},{"id":"2303.08446","title":"Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification","created":"2023-03-15","cited_by_count":54},{"id":"2303.15935","title":"When Brain-inspired AI Meets AGI","created":"2023-03-28","cited_by_count":54},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","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":"2304.01938","title":"Evaluating Large Language Models on a Highly-specialized Topic, Radiation Oncology Physics","created":"2023-04-01","cited_by_count":49},{"id":"1506.04416","title":"Bayesian Dark Knowledge","created":"2015-06-14","cited_by_count":45},{"id":"2405.08603","title":"A Comprehensive Survey of Large Language Models and Multimodal Large Language Models in Medicine","created":"2024-05-14","cited_by_count":45},{"id":"2402.15061","title":"Fine-tuning Large Language Models for Domain-specific Machine Translation","created":"2024-02-23","cited_by_count":43},{"id":"2205.05789","title":"RITA: a Study on Scaling Up Generative Protein Sequence Models","created":"2022-05-11","cited_by_count":42},{"id":"2309.06419","title":"Radiology-Llama2: Best-in-Class Large Language Model for Radiology","created":"2023-08-29","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":"2306.10095","title":"AD-AutoGPT: An Autonomous GPT for Alzheimer's Disease Infodemiology","created":"2023-06-16","cited_by_count":34},{"id":"2312.07399","title":"Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales","created":"2023-12-12","cited_by_count":33},{"id":"2301.12031","title":"Context Matters: A Strategy to Pre-train Language Model for Science Education","created":"2023-01-27","cited_by_count":32},{"id":"2304.09138","title":"Exploring the Trade-Offs: Unified Large Language Models vs Local Fine-Tuned Models for Highly-Specific Radiology NLI Task","created":"2023-04-18","cited_by_count":32},{"id":"2306.05480","title":"Artificial General Intelligence for Medical Imaging Analysis","created":"2023-06-08","cited_by_count":32},{"id":"2306.06156","title":"PoET: A generative model of protein families as sequences-of-sequences","created":"2023-06-09","cited_by_count":29},{"id":"2403.13313","title":"Polaris: A Safety-focused LLM Constellation Architecture for Healthcare","created":"2024-03-20","cited_by_count":28},{"id":"2401.18006","title":"EEG-GPT: Exploring Capabilities of Large Language Models for EEG Classification and Interpretation","created":"2024-01-31","cited_by_count":27},{"id":"2412.04497","title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","created":"2024-11-30","cited_by_count":27},{"id":"2304.11567","title":"Differentiate ChatGPT-generated and Human-written Medical Texts","created":"2023-04-23","cited_by_count":26},{"id":"2407.16154","title":"DDK: Distilling Domain Knowledge for Efficient Large Language Models","created":"2024-07-23","cited_by_count":26},{"id":"2406.06316","title":"Tx-LLM: A Large Language Model for Therapeutics","created":"2024-06-10","cited_by_count":25},{"id":"2106.13058","title":"Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design","created":"2021-06-24","cited_by_count":23},{"id":"2306.11892","title":"Exploring New Frontiers in Agricultural NLP: Investigating the Potential of Large Language Models for Food Applications","created":"2023-06-20","cited_by_count":21},{"id":"2312.06037","title":"Multimodality of AI for Education: Towards Artificial General Intelligence","created":"2023-12-10","cited_by_count":21},{"id":"2402.11398","title":"Reasoning before Comparison: LLM-Enhanced Semantic Similarity Metrics for Domain Specialized Text Analysis","created":"2024-02-17","cited_by_count":21},{"id":"2211.02849","title":"Coarse-to-fine Knowledge Graph Domain Adaptation based on Distantly-supervised Iterative Training","created":"2022-11-05","cited_by_count":20},{"id":"2311.01908","title":"LLM-driven Multimodal Target Volume Contouring in Radiation Oncology","created":"2023-11-03","cited_by_count":20},{"id":"2307.11346","title":"CohortGPT: An Enhanced GPT for Participant Recruitment in Clinical Study","created":"2023-07-21","cited_by_count":19},{"id":"2312.05256","title":"Holistic Evaluation of GPT-4V for Biomedical Imaging","created":"2023-11-10","cited_by_count":19},{"id":"2309.10160","title":"RadOnc-GPT: A Large Language Model for Radiation Oncology","created":"2023-09-18","cited_by_count":18},{"id":"2309.10238","title":"PolicyGPT: Automated Analysis of Privacy Policies with Large Language Models","created":"2023-09-19","cited_by_count":16},{"id":"2410.21287","title":"A Systematic Assessment of OpenAI o1-Preview for Higher Order Thinking in Education","created":"2024-10-11","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":"2312.17016","title":"On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications","created":"2023-12-23","cited_by_count":15},{"id":"2401.12983","title":"Assessing Large Language Models in Mechanical Engineering Education: A Study on Mechanics-Focused Conceptual Understanding","created":"2024-01-13","cited_by_count":15},{"id":"2305.00201","title":"Instruction-ViT: Multi-Modal Prompts for Instruction Learning in ViT","created":"2023-04-29","cited_by_count":14},{"id":"2309.07438","title":"Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges","created":"2023-09-14","cited_by_count":14},{"id":"2310.05242","title":"ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data","created":"2023-10-08","cited_by_count":14},{"id":"2307.02514","title":"Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data","created":"2023-07-05","cited_by_count":13},{"id":"2411.11295","title":"Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation","created":"2024-11-18","cited_by_count":12},{"id":"2406.14898","title":"Safely Learning with Private Data: A Federated Learning Framework for Large Language Model","created":"2024-06-21","cited_by_count":11}],"next_cursor":"100"}