{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"2211.17192","title":"Fast Inference from Transformers via Speculative Decoding","created":"2022-11-30","cited_by_count":1653},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"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":"2302.11939","title":"One Fits All:Power General Time Series Analysis by Pretrained LM","created":"2023-02-23","cited_by_count":632},{"id":"2303.06865","title":"FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU","created":"2023-03-13","cited_by_count":575},{"id":"2310.12931","title":"Eureka: Human-Level Reward Design via Coding Large Language Models","created":"2023-10-19","cited_by_count":571},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"2207.07061","title":"Confident Adaptive Language Modeling","created":"2022-07-14","cited_by_count":310},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2303.00001","title":"Reward Design with Language Models","created":"2023-02-27","cited_by_count":261},{"id":"2407.19669","title":"mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval","created":"2024-07-29","cited_by_count":236},{"id":"2402.05120","title":"More Agents Is All You Need","created":"2024-02-03","cited_by_count":180},{"id":"2210.08964","title":"PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting","created":"2022-09-20","cited_by_count":172},{"id":"1910.05316","title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","created":"2019-10-04","cited_by_count":152},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"2308.08469","title":"LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters","created":"2023-08-16","cited_by_count":129},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2212.11140","title":"Benchmarking Large Language Models for Automated Verilog RTL Code Generation","created":"2022-12-13","cited_by_count":115},{"id":"2102.04170","title":"Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach","created":"2021-02-08","cited_by_count":110},{"id":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83},{"id":"2401.14351","title":"ServerlessLLM: Low-Latency Serverless Inference for Large Language Models","created":"2024-01-25","cited_by_count":80},{"id":"2402.02338","title":"NetLLM: Adapting Large Language Models for Networking","created":"2024-02-04","cited_by_count":78},{"id":"2202.06335","title":"ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification","created":"2022-02-13","cited_by_count":66},{"id":"2204.02685","title":"SecureBERT: A Domain-Specific Language Model for Cybersecurity","created":"2022-04-06","cited_by_count":60},{"id":"2305.19234","title":"Grammar Prompting for Domain-Specific Language Generation with Large Language Models","created":"2023-05-30","cited_by_count":58},{"id":"2404.07413","title":"JetMoE: Reaching Llama2 Performance with 0.1M Dollars","created":"2024-04-11","cited_by_count":57},{"id":"2306.14263","title":"Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices","created":"2023-06-25","cited_by_count":39},{"id":"2310.06116","title":"OptiMUS: Optimization Modeling Using MIP Solvers and large language models","created":"2023-10-09","cited_by_count":39},{"id":"2309.06687","title":"Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Robotics","created":"2023-09-13","cited_by_count":36},{"id":"2310.05204","title":"Towards Optimizing with Large Language Models","created":"2023-10-08","cited_by_count":35},{"id":"2306.07933","title":"Understanding Telecom Language Through Large Language Models","created":"2023-06-09","cited_by_count":32},{"id":"2307.04945","title":"What do LLMs need to Synthesize Correct Router Configurations?","created":"2023-07-11","cited_by_count":29},{"id":"2310.12541","title":"Large Language Model for Multi-objective Evolutionary Optimization","created":"2023-10-19","cited_by_count":29},{"id":"2308.12923","title":"Diagnosing Infeasible Optimization Problems Using Large Language Models","created":"2023-08-23","cited_by_count":27},{"id":"2307.07319","title":"The Power of Large Language Models for Wireless Communication System Development: A Case Study on FPGA Platforms","created":"2023-07-14","cited_by_count":20},{"id":"2308.06261","title":"Enhancing Network Management Using Code Generated by Large Language Models","created":"2023-08-11","cited_by_count":20},{"id":"2401.13920","title":"LocMoE: A Low-Overhead MoE for Large Language Model Training","created":"2024-01-25","cited_by_count":19},{"id":"2403.05826","title":"Cached Model-as-a-Resource: Provisioning Large Language Model Agents for Edge Intelligence in Space-air-ground Integrated Networks","created":"2024-03-09","cited_by_count":15},{"id":"2402.10067","title":"LLM-based policy generation for intent-based management of applications","created":"2024-01-22","cited_by_count":13},{"id":"2305.13102","title":"Observations on LLMs for Telecom Domain: Capabilities and Limitations","created":"2023-05-22","cited_by_count":11},{"id":"2412.15690","title":"Theory of Mixture-of-Experts for Mobile Edge Computing","created":"2024-12-20","cited_by_count":5},{"id":"2309.04716","title":"Toward Reproducing Network Research Results Using Large Language Models","created":"2023-09-09","cited_by_count":3}],"next_cursor":null}