{"list":"other","total":55,"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2212.08073","title":"Constitutional AI: Harmlessness from AI Feedback","created":"2022-12-15","cited_by_count":3050},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2401.04088","title":"Mixtral of Experts","created":"2024-01-08","cited_by_count":1823},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1508.04025","title":"Effective Approaches to Attention-based Neural Machine Translation","created":"2015-08-17","cited_by_count":1026},{"id":"1906.04341","title":"What Does BERT Look At? An Analysis of BERT's Attention","created":"2019-06-11","cited_by_count":1003},{"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":"2301.00234","title":"A Survey on In-context Learning","created":"2022-12-31","cited_by_count":721},{"id":"2103.10385","title":"GPT Understands, Too","created":"2021-03-18","cited_by_count":716},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2303.13375","title":"Capabilities of GPT-4 on Medical Challenge Problems","created":"2023-03-20","cited_by_count":638},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"1506.07503","title":"Attention-Based Models for Speech Recognition","created":"2015-06-24","cited_by_count":401},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387},{"id":"2105.06643","title":"Monash Time Series Forecasting Archive","created":"2021-05-14","cited_by_count":267},{"id":"2010.15980","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","created":"2020-10-29","cited_by_count":249},{"id":"2002.09291","title":"Transformer Hawkes Process","created":"2020-02-21","cited_by_count":235},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2308.11730","title":"Knowledge Graph Prompting for Multi-Document Question Answering","created":"2023-08-22","cited_by_count":152},{"id":"1806.11146","title":"Adversarial Reprogramming of Neural Networks","created":"2018-06-28","cited_by_count":116},{"id":"2302.00861","title":"SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling","created":"2023-02-02","cited_by_count":115},{"id":"2201.00044","title":"Transformer Embeddings of Irregularly Spaced Events and Their Participants","created":"2021-12-31","cited_by_count":93},{"id":"2110.03224","title":"Darts: User-Friendly Modern Machine Learning for Time Series","created":"2021-10-07","cited_by_count":91},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2305.16646","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","created":"2023-05-26","cited_by_count":45},{"id":"2402.01763","title":"When Large Language Models Meet Vector Databases: A Survey","created":"2024-01-30","cited_by_count":39},{"id":"2209.10222","title":"Fairness Reprogramming","created":"2022-09-21","cited_by_count":33},{"id":"2310.04993","title":"Prompt-augmented Temporal Point Process for Streaming Event Sequence","created":"2023-10-08","cited_by_count":24},{"id":"2402.07429","title":"Particle Filter SLAM for Vehicle Localization","created":"2024-02-12","cited_by_count":23},{"id":"2402.07422","title":"News Recommendation with Attention Mechanism","created":"2024-02-12","cited_by_count":15},{"id":"2305.10649","title":"ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs","created":"2023-05-18","cited_by_count":13},{"id":"2312.09601","title":"Binary Code Summarization: Benchmarking ChatGPT/GPT-4 and Other Large Language Models","created":"2023-12-15","cited_by_count":13},{"id":"2401.15354","title":"DeepGI: An Automated Approach for Gastrointestinal Tract Segmentation in MRI Scans","created":"2024-01-27","cited_by_count":13},{"id":"2401.00534","title":"Financial Time-Series Forecasting: Towards Synergizing Performance And Interpretability Within a Hybrid Machine Learning Approach","created":"2023-12-31","cited_by_count":10},{"id":"2008.09763","title":"Variational Autoencoder for Anti-Cancer Drug Response Prediction","created":"2020-08-22","cited_by_count":5},{"id":"2303.12135","title":"Understand Legal Documents with Contextualized Large Language Models","created":"2023-03-21","cited_by_count":5},{"id":"2302.03256","title":"Identifying Flakiness in Quantum Programs","created":"2023-02-07","cited_by_count":4},{"id":"2206.07164","title":"Edge Security: Challenges and Issues","created":"2022-06-14","cited_by_count":3},{"id":"2312.13119","title":"Graphene: Infrastructure Security Posture Analysis with AI-generated Attack Graphs","created":"2023-12-20","cited_by_count":3},{"id":"2311.17705","title":"Q-PAC: Automated Detection of Quantum Bug-Fix Patterns","created":"2023-11-29","cited_by_count":1}],"next_cursor":null}