{"list":"other","total":86,"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":"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":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"2305.10601","title":"Tree of Thoughts: Deliberate Problem Solving with Large Language Models","created":"2023-05-17","cited_by_count":3211},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"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":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2308.09687","title":"Graph of Thoughts: Solving Elaborate Problems with Large Language Models","created":"2023-08-18","cited_by_count":886},{"id":"1912.09363","title":"Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting","created":"2019-12-19","cited_by_count":761},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2310.01728","title":"Time-LLM: Time Series Forecasting by Reprogramming Large Language Models","created":"2023-10-03","cited_by_count":700},{"id":"2310.10688","title":"A decoder-only foundation model for time-series forecasting","created":"2023-10-14","cited_by_count":692},{"id":"2305.11627","title":"LLM-Pruner: On the Structural Pruning of Large Language Models","created":"2023-05-19","cited_by_count":650},{"id":"2310.07820","title":"Large Language Models Are Zero-Shot Time Series Forecasters","created":"2023-10-11","cited_by_count":500},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2212.10071","title":"Large Language Models Are Reasoning Teachers","created":"2022-12-20","cited_by_count":329},{"id":"2305.17888","title":"LLM-QAT: Data-Free Quantization Aware Training for Large Language Models","created":"2023-05-29","cited_by_count":324},{"id":"2308.07633","title":"A Survey on Model Compression for Large Language Models","created":"2023-08-15","cited_by_count":269},{"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":"2306.09364","title":"TSMixer: Lightweight MLP-Mixer Model for Multivariate Time Series Forecasting","created":"2023-06-14","cited_by_count":139},{"id":"2308.08469","title":"LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters","created":"2023-08-16","cited_by_count":129},{"id":"2206.09113","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-06-18","cited_by_count":117},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"id":"2402.01801","title":"Large Language Models for Time Series: A Survey","created":"2024-02-02","cited_by_count":114},{"id":"2310.08278","title":"Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting","created":"2023-10-12","cited_by_count":113},{"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":"2403.07300","title":"CALF: Aligning LLMs for Time Series Forecasting via Cross-modal Fine-Tuning","created":"2024-03-12","cited_by_count":108},{"id":"2104.03466","title":"Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT","created":"2021-04-08","cited_by_count":104},{"id":"2412.03104","title":"ChatTS: Aligning Time Series with LLMs via Synthetic Data for Enhanced Understanding and Reasoning","created":"2024-12-04","cited_by_count":103},{"id":"2409.17515","title":"From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection","created":"2024-09-26","cited_by_count":98},{"id":"2403.00131","title":"UniTS: A Unified Multi-Task Time Series Model","created":"2024-02-29","cited_by_count":94},{"id":"2410.20724","title":"Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation","created":"2024-10-28","cited_by_count":80},{"id":"2306.11025","title":"Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting","created":"2023-06-19","cited_by_count":77},{"id":"2410.08815","title":"StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization","created":"2024-10-11","cited_by_count":71},{"id":"2403.15042","title":"LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement","created":"2024-03-22","cited_by_count":70},{"id":"2112.02690","title":"Open Vocabulary Electroencephalography-To-Text Decoding and Zero-shot Sentiment Classification","created":"2021-12-05","cited_by_count":67},{"id":"2401.06866","title":"Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data","created":"2024-01-12","cited_by_count":66},{"id":"2202.10629","title":"Model Reprogramming: Resource-Efficient Cross-Domain Machine Learning","created":"2022-02-22","cited_by_count":64},{"id":"2407.04675","title":"Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition","created":"2024-07-05","cited_by_count":63},{"id":"2402.03182","title":"Empowering Time Series Analysis with Large Language Models: A Survey","created":"2024-02-05","cited_by_count":60},{"id":"1701.01887","title":"Deep Learning for Time-Series Analysis","created":"2017-01-07","cited_by_count":55},{"id":"2409.00097","title":"Large Language Models for Disease Diagnosis: A Scoping Review","created":"2024-08-27","cited_by_count":51},{"id":"2302.12721","title":"LightTS: Lightweight Time Series Classification with Adaptive Ensemble Distillation -- Extended Version","created":"2023-02-24","cited_by_count":50},{"id":"2402.10835","title":"Time Series Forecasting with LLMs: Understanding and Enhancing Model Capabilities","created":"2024-02-16","cited_by_count":48},{"id":"2205.15308","title":"Parameter-Efficient and Student-Friendly Knowledge Distillation","created":"2022-05-28","cited_by_count":47},{"id":"2402.02713","title":"Position: What Can Large Language Models Tell Us about Time Series Analysis","created":"2024-02-05","cited_by_count":47},{"id":"2411.08249","title":"Retrieval Augmented Time Series Forecasting","created":"2024-11-12","cited_by_count":46},{"id":"2305.16646","title":"Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning","created":"2023-05-26","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":"2405.15319","title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","created":"2024-05-24","cited_by_count":43},{"id":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42},{"id":"2503.01013","title":"TimeXL: Explainable Multi-modal Time Series Prediction with LLM-in-the-Loop","created":"2025-03-02","cited_by_count":39},{"id":"2212.10670","title":"In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models","created":"2022-12-20","cited_by_count":37},{"id":"2409.11376","title":"Towards Time Series Reasoning with LLMs","created":"2024-09-17","cited_by_count":37},{"id":"2205.03776","title":"SparseTT: Visual Tracking with Sparse Transformers","created":"2022-05-08","cited_by_count":36},{"id":"2405.14755","title":"Large language models can be zero-shot anomaly detectors for time series?","created":"2024-05-23","cited_by_count":31},{"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":"2401.15123","title":"Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection","created":"2024-01-26","cited_by_count":26},{"id":"2405.14252","title":"Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting","created":"2024-05-23","cited_by_count":26},{"id":"2310.04993","title":"Prompt-augmented Temporal Point Process for Streaming Event Sequence","created":"2023-10-08","cited_by_count":24},{"id":"1909.07155","title":"Meta-Learning for Few-Shot Time Series Classification","created":"2019-09-13","cited_by_count":23},{"id":"2405.02358","title":"Empowering Time Series Analysis with Foundation Models: A Comprehensive Survey","created":"2024-05-03","cited_by_count":23},{"id":"2412.16643","title":"TimeRAG: BOOSTING LLM Time Series Forecasting via Retrieval-Augmented Generation","created":"2024-12-21","cited_by_count":21},{"id":"2412.20810","title":"TimeRAF: Retrieval-Augmented Foundation model for Zero-shot Time Series Forecasting","created":"2024-12-30","cited_by_count":17},{"id":"2408.07773","title":"MedTsLLM: Leveraging LLMs for Multimodal Medical Time Series Analysis","created":"2024-08-14","cited_by_count":15},{"id":"2502.15016","title":"TimeDistill: Efficient Long-Term Time Series Forecasting with MLP via Cross-Architecture Distillation","created":"2025-02-20","cited_by_count":12},{"id":"2210.02199","title":"MTSMAE: Masked Autoencoders for Multivariate Time-Series Forecasting","created":"2022-10-04","cited_by_count":9},{"id":"2407.03689","title":"Text2TimeSeries: Enhancing Financial Forecasting through Time Series Prediction Updates with Event-Driven Insights from Large Language Models","created":"2024-07-04","cited_by_count":9},{"id":"2410.02062","title":"TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models","created":"2024-10-02","cited_by_count":9},{"id":"2410.18686","title":"Hierarchical Multimodal LLMs with Semantic Space Alignment for Enhanced Time Series Classification","created":"2024-10-24","cited_by_count":7},{"id":"2406.08765","title":"LLM-based Knowledge Pruning for Time Series Data Analytics on Edge-computing Devices","created":"2024-06-13","cited_by_count":6},{"id":"2501.06386","title":"Using Pre-trained LLMs for Multivariate Time Series Forecasting","created":"2025-01-10","cited_by_count":6},{"id":"2502.16627","title":"Energy-Efficient Transformer Inference: Optimization Strategies for Time Series Classification","created":"2025-02-23","cited_by_count":2},{"id":"2503.04150","title":"Temporal Alignment of LLMs through Cycle Encoding for Long-Range Time Representations","created":"2025-03-06","cited_by_count":2},{"id":"2404.19319","title":"Knowledge Distillation vs. Pretraining from Scratch under a Fixed (Computation) Budget","created":"2024-04-30","cited_by_count":1}],"next_cursor":null}