{"list":"other","total":81,"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":"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":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2106.07447","title":"HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units","created":"2021-06-14","cited_by_count":2342},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"2307.16789","title":"ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs","created":"2023-07-31","cited_by_count":1947},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"1912.06670","title":"Common Voice: A Massively-Multilingual Speech Corpus","created":"2019-12-13","cited_by_count":1384},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2303.17564","title":"BloombergGPT: A Large Language Model for Finance","created":"2023-03-30","cited_by_count":939},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2209.03143","title":"AudioLM: a Language Modeling Approach to Audio Generation","created":"2022-09-07","cited_by_count":616},{"id":"2301.06052","title":"T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations","created":"2023-01-15","cited_by_count":588},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"2310.13289","title":"SALMONN: Towards Generic Hearing Abilities for Large Language Models","created":"2023-10-20","cited_by_count":506},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2202.07125","title":"Transformers in Time Series: A Survey","created":"2022-02-15","cited_by_count":497},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1912.07875","title":"Libri-Light: A Benchmark for ASR with Limited or No Supervision","created":"2019-12-17","cited_by_count":467},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"1912.10077","title":"Are Transformers universal approximators of sequence-to-sequence functions?","created":"2019-12-20","cited_by_count":406},{"id":"2306.12925","title":"AudioPaLM: A Large Language Model That Can Speak and Listen","created":"2023-06-22","cited_by_count":343},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"2310.02207","title":"Language Models Represent Space and Time","created":"2023-10-03","cited_by_count":316},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295},{"id":"2210.10723","title":"TabLLM: Few-shot Classification of Tabular Data with Large Language Models","created":"2022-10-19","cited_by_count":277},{"id":"2306.05443","title":"PIXIU: A Large Language Model, Instruction Data and Evaluation Benchmark for Finance","created":"2023-06-08","cited_by_count":222},{"id":"2305.10790","title":"Listen, Think, and Understand","created":"2023-05-18","cited_by_count":209},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2310.04948","title":"TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting","created":"2023-10-08","cited_by_count":174},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"2308.08241","title":"TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series","created":"2023-08-16","cited_by_count":169},{"id":"2206.06565","title":"LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks","created":"2022-06-14","cited_by_count":148},{"id":"2310.09751","title":"UniTime: A Language-Empowered Unified Model for Cross-Domain Time Series Forecasting","created":"2023-10-15","cited_by_count":144},{"id":"2310.00704","title":"UniAudio: An Audio Foundation Model Toward Universal Audio Generation","created":"2023-10-01","cited_by_count":127},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118},{"id":"2306.06344","title":"Language-Guided Traffic Simulation via Scene-Level Diffusion","created":"2023-06-10","cited_by_count":111},{"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":"2308.15197","title":"Where Would I Go Next? Large Language Models as Human Mobility Predictors","created":"2023-08-29","cited_by_count":93},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2305.16107","title":"VioLA: Unified Codec Language Models for Speech Recognition, Synthesis, and Translation","created":"2023-05-25","cited_by_count":87},{"id":"2401.10134","title":"Spatial-Temporal Large Language Model for Traffic Prediction","created":"2024-01-18","cited_by_count":83},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77},{"id":"2308.11276","title":"Music Understanding LLaMA: Advancing Text-to-Music Generation with Question Answering and Captioning","created":"2023-08-22","cited_by_count":77},{"id":"2112.02690","title":"Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification","created":"2021-12-05","cited_by_count":67},{"id":"1912.00903","title":"ZuCo 2.0: A Dataset of Physiological Recordings During Natural Reading and Annotation","created":"2019-12-02","cited_by_count":66},{"id":"2303.12311","title":"Frozen Language Model Helps ECG Zero-Shot Learning","created":"2023-03-22","cited_by_count":62},{"id":"2304.05351","title":"The Wall Street Neophyte: A Zero-Shot Analysis of ChatGPT Over MultiModal Stock Movement Prediction Challenges","created":"2023-04-10","cited_by_count":59},{"id":"2306.15681","title":"ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram","created":"2023-06-21","cited_by_count":54},{"id":"2305.10716","title":"A Survey on Time-Series Pre-Trained Models","created":"2023-05-18","cited_by_count":52},{"id":"2209.05479","title":"Leveraging Language Foundation Models for Human Mobility Forecasting","created":"2022-09-11","cited_by_count":50},{"id":"2210.14395","title":"IMU2CLIP: Multimodal Contrastive Learning for IMU Motion Sensors from Egocentric Videos and Text","created":"2022-10-26","cited_by_count":37},{"id":"2311.14332","title":"GATGPT: A Pre-trained Large Language Model with Graph Attention Network for Spatiotemporal Imputation","created":"2023-11-24","cited_by_count":35},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34},{"id":"2309.07145","title":"ETP: Learning Transferable ECG Representations via ECG-Text Pre-training","created":"2023-09-06","cited_by_count":29},{"id":"2310.04942","title":"Large Language Models for Spatial Trajectory Patterns Mining","created":"2023-10-07","cited_by_count":27},{"id":"2203.15863","title":"WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models","created":"2022-03-29","cited_by_count":26},{"id":"2311.08245","title":"TENT: Connect Language Models with IoT Sensors for Zero-Shot Activity Recognition","created":"2023-11-14","cited_by_count":25},{"id":"2301.10166","title":"Leveraging Vision-Language Models for Granular Market Change Prediction","created":"2023-01-17","cited_by_count":22},{"id":"2309.10917","title":"End-to-End Speech Recognition Contextualization with Large Language Models","created":"2023-09-19","cited_by_count":22},{"id":"2312.06855","title":"Multimodal Pretraining of Medical Time Series and Notes","created":"2023-12-11","cited_by_count":22},{"id":"2301.09017","title":"Transfer Knowledge from Natural Language to Electrocardiography: Can We Detect Cardiovascular Disease Through Language Models?","created":"2023-01-21","cited_by_count":21},{"id":"2305.03187","title":"Generating Virtual On-body Accelerometer Data from Virtual Textual Descriptions for Human Activity Recognition","created":"2023-05-04","cited_by_count":19},{"id":"2005.10111","title":"The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models","created":"2020-05-20","cited_by_count":18},{"id":"2310.05627","title":"Integrating Stock Features and Global Information via Large Language Models for Enhanced Stock Return Prediction","created":"2023-10-09","cited_by_count":17},{"id":"2303.09395","title":"Text-to-ECG: 12-Lead Electrocardiogram Synthesis conditioned on Clinical Text Reports","created":"2023-03-09","cited_by_count":14},{"id":"2310.20034","title":"GG-LLM: Geometrically Grounding Large Language Models for Zero-shot Human Activity Forecasting in Human-Aware Task Planning","created":"2023-10-30","cited_by_count":13},{"id":"2301.03462","title":"Unleashing the Power of Shared Label Structures for Human Activity Recognition","created":"2023-01-01","cited_by_count":7},{"id":"2310.17788","title":"Utilizing Language Models for Energy Load Forecasting","created":"2023-10-26","cited_by_count":7},{"id":"2301.00489","title":"Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework","created":"2023-01-01","cited_by_count":6}],"next_cursor":null}