{"list":"other","total":69,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"2307.06435","title":"A Comprehensive Overview of Large Language Models","created":"2023-07-12","cited_by_count":648},{"id":"2404.14618","title":"Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing","created":"2024-04-22","cited_by_count":372},{"id":"2402.13116","title":"A Survey on Knowledge Distillation of Large Language Models","created":"2024-02-20","cited_by_count":284},{"id":"2408.07666","title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","created":"2024-08-14","cited_by_count":254},{"id":"2406.02818","title":"Chain of Agents: Large Language Models Collaborating on Long-Context Tasks","created":"2024-06-04","cited_by_count":206},{"id":"2501.01957","title":"VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction","created":"2025-01-03","cited_by_count":197},{"id":"2406.03243","title":"Llumnix: Dynamic Scheduling for Large Language Model Serving","created":"2024-06-05","cited_by_count":174},{"id":"2407.18921","title":"Mobile Edge Intelligence for Large Language Models: A Contemporary Survey","created":"2024-07-09","cited_by_count":128},{"id":"2401.10491","title":"Knowledge Fusion of Large Language Models","created":"2024-01-19","cited_by_count":115},{"id":"2406.15951","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","created":"2024-06-22","cited_by_count":113},{"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":"2502.18036","title":"Harnessing Multiple Large Language Models: A Survey on LLM Ensemble","created":"2025-02-25","cited_by_count":86},{"id":"2503.09501","title":"ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning","created":"2025-03-12","cited_by_count":79},{"id":"2502.18482","title":"MixLLM: Dynamic Routing in Mixed Large Language Models","created":"2025-02-09","cited_by_count":59},{"id":"2404.11531","title":"Pack of LLMs: Model Fusion at Test-Time via Perplexity Optimization","created":"2024-04-17","cited_by_count":56},{"id":"2404.02418","title":"Auxiliary task demands mask the capabilities of smaller language models","created":"2024-04-03","cited_by_count":54},{"id":"2402.09269","title":"Personalized Large Language Models","created":"2024-02-14","cited_by_count":44},{"id":"2403.19076","title":"Tiny Machine Learning: Progress and Futures","created":"2024-03-28","cited_by_count":40},{"id":"2502.05177","title":"Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy","created":"2025-02-07","cited_by_count":39},{"id":"2401.13979","title":"Routoo: Learning to Route to Large Language Models Effectively","created":"2024-01-25","cited_by_count":34},{"id":"2403.03129","title":"CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following","created":"2024-03-05","cited_by_count":33},{"id":"2503.05659","title":"A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval","created":"2025-03-07","cited_by_count":33},{"id":"2412.04692","title":"Smoothie: Label Free Language Model Routing","created":"2024-12-06","cited_by_count":31},{"id":"2502.01976","title":"CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing","created":"2025-02-04","cited_by_count":30},{"id":"2503.16212","title":"MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion","created":"2025-03-20","cited_by_count":30},{"id":"2502.04428","title":"Confident or Seek Stronger: Exploring Uncertainty-Based On-device LLM Routing From Benchmarking to Generalization","created":"2025-02-06","cited_by_count":29},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25},{"id":"2412.19823","title":"A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions","created":"2024-12-16","cited_by_count":25},{"id":"2502.04392","title":"Division-of-Thoughts: Harnessing Hybrid Language Model Synergy for Efficient On-Device Agents","created":"2025-02-06","cited_by_count":25},{"id":"2501.16254","title":"Multi-Agent Geospatial Copilots for Remote Sensing Workflows","created":"2025-01-27","cited_by_count":22},{"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":"2502.15964","title":"Minions: Cost-efficient Collaboration Between On-device and Cloud Language Models","created":"2025-02-21","cited_by_count":20},{"id":"2504.04915","title":"Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration","created":"2025-04-07","cited_by_count":20},{"id":"2405.17890","title":"SLMRec: Distilling Large Language Models into Small for Sequential Recommendation","created":"2024-05-28","cited_by_count":18},{"id":"2404.04286","title":"Bias Amplification in Language Model Evolution: An Iterated Learning Perspective","created":"2024-04-04","cited_by_count":17},{"id":"2504.21716","title":"LLM-Empowered Embodied Agent for Memory-Augmented Task Planning in Household Robotics","created":"2025-04-30","cited_by_count":17},{"id":"2501.05647","title":"Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation","created":"2025-01-10","cited_by_count":15},{"id":"2504.02051","title":"Self-Resource Allocation in Multi-Agent LLM Systems","created":"2025-04-02","cited_by_count":15},{"id":"2312.05842","title":"Mutual Enhancement of Large and Small Language Models with Cross-Silo Knowledge Transfer","created":"2023-12-10","cited_by_count":13},{"id":"2406.12295","title":"Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding","created":"2024-06-18","cited_by_count":13},{"id":"2502.15336","title":"Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions","created":"2025-02-21","cited_by_count":13},{"id":"2502.15924","title":"Improving Consistency in Large Language Models through Chain of Guidance","created":"2025-02-21","cited_by_count":13},{"id":"2407.06573","title":"LLM for Mobile: An Initial Roadmap","created":"2024-07-09","cited_by_count":11},{"id":"2409.12545","title":"Enhancing Knowledge Distillation of Large Language Models through Efficient Multi-Modal Distribution Alignment","created":"2024-09-19","cited_by_count":11},{"id":"2503.08704","title":"Life-Cycle Routing Vulnerabilities of LLM Router","created":"2025-03-09","cited_by_count":11},{"id":"2504.00424","title":"Hawkeye:Efficient Reasoning with Model Collaboration","created":"2025-04-01","cited_by_count":11},{"id":"2502.14816","title":"Dynamic Low-Rank Sparse Adaptation for Large Language Models","created":"2025-02-20","cited_by_count":10},{"id":"2502.19159","title":"Sliding-Window Merging for Compacting Patch-Redundant Layers in LLMs","created":"2025-02-26","cited_by_count":9},{"id":"2502.08020","title":"Speculate, then Collaborate: Fusing Knowledge of Language Models during Decoding","created":"2025-02-11","cited_by_count":8},{"id":"2407.20970","title":"Large Language Models (LLMs) for Semantic Communication in Edge-based IoT Networks","created":"2024-07-30","cited_by_count":7},{"id":"2504.04569","title":"KnowsLM: A framework for evaluation of small language models for knowledge augmentation and humanised conversations","created":"2025-04-06","cited_by_count":6},{"id":"2504.10519","title":"Toward Super Agent System with Hybrid AI Routers","created":"2025-04-11","cited_by_count":6},{"id":"2411.11707","title":"Federated Co-tuning Framework for Large and Small Language Models","created":"2024-11-18","cited_by_count":5},{"id":"2503.04201","title":"Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition","created":"2025-03-06","cited_by_count":5},{"id":"2404.11072","title":"Large Language Models Meet User Interfaces: The Case of Provisioning Feedback","created":"2024-04-17","cited_by_count":4},{"id":"2405.03821","title":"Thoughtful Things: Building Human-Centric Smart Devices with Small Language Models","created":"2024-05-06","cited_by_count":4},{"id":"2410.21868","title":"Improving In-Context Learning with Small Language Model Ensembles","created":"2024-10-29","cited_by_count":4},{"id":"2504.17421","title":"Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks","created":"2025-04-24","cited_by_count":4},{"id":"2402.05333","title":"ML-Enabled Systems Model Deployment and Monitoring: Status Quo and Problems","created":"2024-02-08","cited_by_count":3},{"id":"2408.04998","title":"ProFuser: Progressive Fusion of Large Language Models","created":"2024-08-09","cited_by_count":3},{"id":"2504.11082","title":"DeepMLF: Multimodal language model with learnable tokens for deep fusion in sentiment analysis","created":"2025-04-15","cited_by_count":3},{"id":"2502.19954","title":"Collaborative Stance Detection via Small-Large Language Model Consistency Verification","created":"2025-02-27","cited_by_count":2},{"id":"2504.15300","title":"Collaborative Learning of On-Device Small Model and Cloud-Based Large Model: Advances and Future Directions","created":"2025-04-17","cited_by_count":2},{"id":"2504.16056","title":"Honey, I Shrunk the Language Model: Impact of Knowledge Distillation Methods on Performance and Explainability","created":"2025-04-22","cited_by_count":2},{"id":"2412.03772","title":"A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devices","created":"2024-12-04","cited_by_count":1},{"id":"2502.09854","title":"Scaling Multimodal Search and Recommendation with Small Language Models via Upside-Down Reinforcement Learning","created":"2025-02-14","cited_by_count":1}],"next_cursor":null}