{"list":"other","total":79,"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":"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"2305.05176","title":"FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance","created":"2023-05-09","cited_by_count":853},{"id":"2406.18665","title":"RouteLLM: Learning to Route LLMs with Preference Data","created":"2024-06-26","cited_by_count":682},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2306.02561","title":"LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion","created":"2023-06-05","cited_by_count":564},{"id":"2305.09617","title":"Towards Expert-Level Medical Question Answering with Large Language Models","created":"2023-05-16","cited_by_count":384},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2401.11817","title":"Hallucination is Inevitable: An Innate Limitation of Large Language Models","created":"2024-01-22","cited_by_count":332},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2301.04856","title":"Multimodal Deep Learning","created":"2023-01-12","cited_by_count":258},{"id":"2403.12031","title":"RouterBench: A Benchmark for Multi-LLM Routing System","created":"2024-03-18","cited_by_count":238},{"id":"2407.06204","title":"A Survey on Mixture of Experts in Large Language Models","created":"2024-06-26","cited_by_count":237},{"id":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2404.14294","title":"A Survey on Efficient Inference for Large Language Models","created":"2024-04-22","cited_by_count":205},{"id":"1806.00187","title":"Scaling Neural Machine Translation","created":"2018-06-01","cited_by_count":204},{"id":"2402.16363","title":"LLM Inference Unveiled: Survey and Roofline Model Insights","created":"2024-02-26","cited_by_count":152},{"id":"2309.00363","title":"FederatedScope-LLM: A Comprehensive Package for Fine-tuning Large Language Models in Federated Learning","created":"2023-09-01","cited_by_count":149},{"id":"2311.08692","title":"Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models","created":"2023-11-15","cited_by_count":145},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2411.03350","title":"A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness","created":"2024-11-04","cited_by_count":127},{"id":"2310.12963","title":"AutoMix: Automatically Mixing Language Models","created":"2023-10-19","cited_by_count":125},{"id":"1904.02874","title":"An Attentive Survey of Attention Models","created":"2019-04-05","cited_by_count":124},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112},{"id":"2012.04373","title":"CrossNER: Evaluating Cross-Domain Named Entity Recognition","created":"2020-12-08","cited_by_count":104},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104},{"id":"2312.15234","title":"Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems","created":"2023-12-23","cited_by_count":102},{"id":"2410.11845","title":"A Review on Edge Large Language Models: Design, Execution, and Applications","created":"2024-09-29","cited_by_count":100},{"id":"2411.13676","title":"Hymba: A Hybrid-head Architecture for Small Language Models","created":"2024-11-20","cited_by_count":99},{"id":"2308.06077","title":"Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling","created":"2023-08-11","cited_by_count":95},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86},{"id":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86},{"id":"2401.00625","title":"Beyond Efficiency: A Systematic Survey of Resource-Efficient Large Language Models","created":"2024-01-01","cited_by_count":67},{"id":"2407.00952","title":"SplitLoRA: A Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","created":"2024-07-01","cited_by_count":62},{"id":"2403.20306","title":"Towards Greener LLMs: Bringing Energy-Efficiency to the Forefront of LLM Inference","created":"2024-03-29","cited_by_count":61},{"id":"2503.10657","title":"RouterEval: A Comprehensive Benchmark for Routing LLMs to Explore Model-level Scaling Up in LLMs","created":"2025-03-08","cited_by_count":61},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51},{"id":"2310.03046","title":"EcoAssistant: Using LLM Assistant More Affordably and Accurately","created":"2023-10-03","cited_by_count":49},{"id":"2405.00467","title":"Harnessing the Power of Multiple Minds: Lessons Learned from LLM Routing","created":"2024-05-01","cited_by_count":46},{"id":"2407.12391","title":"LLM Inference Serving: Survey of Recent Advances and Opportunities","created":"2024-07-17","cited_by_count":46},{"id":"2407.10834","title":"MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMs","created":"2024-07-15","cited_by_count":41},{"id":"2502.00425","title":"MQuant: Unleashing the Inference Potential of Multimodal Large Language Models via Full Static Quantization","created":"2025-02-01","cited_by_count":35},{"id":"2405.02134","title":"Optimising Calls to Large Language Models with Uncertainty-Based Two-Tier Selection","created":"2024-05-03","cited_by_count":33},{"id":"2308.11601","title":"Tryage: Real-time, intelligent Routing of User Prompts to Large Language Models","created":"2023-08-22","cited_by_count":30},{"id":"2312.00678","title":"The Efficiency Spectrum of Large Language Models: An Algorithmic Survey","created":"2023-12-01","cited_by_count":26},{"id":"2404.07584","title":"UltraEval: A Lightweight Platform for Flexible and Comprehensive Evaluation for LLMs","created":"2024-04-11","cited_by_count":24},{"id":"2407.15248","title":"XAI meets LLMs: A Survey of the Relation between Explainable AI and Large Language Models","created":"2024-07-21","cited_by_count":23},{"id":"2402.01799","title":"Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward","created":"2024-02-02","cited_by_count":21},{"id":"2502.00409","title":"Doing More with Less: A Survey on Routing Strategies for Resource Optimisation in Large Language Model-Based Systems","created":"2025-02-01","cited_by_count":20},{"id":"2112.08560","title":"Block-Skim: Efficient Question Answering for Transformer","created":"2021-12-16","cited_by_count":18},{"id":"2410.02486","title":"Encryption-Friendly LLM Architecture","created":"2024-10-03","cited_by_count":17},{"id":"2405.15130","title":"OptLLM: Optimal Assignment of Queries to Large Language Models","created":"2024-05-24","cited_by_count":16},{"id":"2505.07460","title":"A Survey on Collaborative Mechanisms Between Large and Small Language Models","created":"2025-05-12","cited_by_count":14},{"id":"2412.12170","title":"PickLLM: Context-Aware RL-Assisted Large Language Model Routing","created":"2024-12-12","cited_by_count":13},{"id":"2505.16508","title":"Edge-First Language Model Inference: Models, Metrics, and Tradeoffs","created":"2025-05-22","cited_by_count":13},{"id":"2311.10785","title":"Text Sanitization Beyond Specific Domains: Zero-Shot Redaction & Substitution with Large Language Models","created":"2023-11-16","cited_by_count":10},{"id":"2407.07000","title":"Etalon: Holistic Performance Evaluation Framework for LLM Inference Systems","created":"2024-07-09","cited_by_count":10},{"id":"2410.04927","title":"FELLAS: Enhancing Federated Sequential Recommendation with LLM as External Services","created":"2024-10-07","cited_by_count":9},{"id":"2503.14882","title":"Communication-Efficient Distributed On-Device LLM Inference Over Wireless Networks","created":"2025-03-19","cited_by_count":9},{"id":"2310.13561","title":"Cache & Distil: Optimising API Calls to Large Language Models","created":"2023-10-20","cited_by_count":4},{"id":"2408.08564","title":"Collaborative Cross-modal Fusion with Large Language Model for Recommendation","created":"2024-08-16","cited_by_count":4},{"id":"2303.04851","title":"Lexical Complexity Prediction: An Overview","created":"2023-03-08","cited_by_count":3},{"id":"2503.09114","title":"Sometimes Painful but Certainly Promising: Feasibility and Trade-offs of Language Model Inference at the Edge","created":"2025-03-12","cited_by_count":3},{"id":"2409.13757","title":"Efficient Hybrid Inference for LLMs: Reward-Based Token Modelling with Selective Cloud Assistance","created":"2024-09-15","cited_by_count":2},{"id":"2504.08764","title":"Evaluation of the phi-3-mini SLM for identification of texts related to medicine, health, and sports injuries","created":"2025-03-31","cited_by_count":2}],"next_cursor":null}