{"total":52,"rows":[{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2410.13638","title":"Scaling Wearable Foundation Models","created":"2024-10-17","cited_by_count":63,"area":null},{"id":"2503.06027","title":"Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Models","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2410.08014","title":"Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2510.13890","title":"A Survey on Collaborating Small and Large Language Models for Performance, Cost-effectiveness, Cloud-edge Privacy, and Trustworthiness","created":"2025-10-14","cited_by_count":7,"area":null},{"id":"2602.05902","title":"CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2506.06579","title":"Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques","created":"2025-06-06","cited_by_count":5,"area":null},{"id":"2503.12167","title":"PLM: Efficient Peripheral Language Models Hardware-Co-Designed for Ubiquitous Computing","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2503.21412","title":"Federated Intelligence: When Large AI Models Meet Federated Fine-Tuning and Collaborative Reasoning at the Network Edge","created":"2025-03-27","cited_by_count":4,"area":null},{"id":"2509.09097","title":"DP-FedLoRA: Privacy-Enhanced Federated Fine-Tuning for On-Device Large Language Models","created":"2025-09-11","cited_by_count":4,"area":null},{"id":"2601.20323","title":"ECG-Agent: On-Device Tool-Calling Agent for ECG Multi-Turn Dialogue","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2505.04174","title":"On-Device LLM for Context-Aware Wi-Fi Roaming","created":"2025-05-07","cited_by_count":3,"area":null},{"id":"2505.06461","title":"Challenging GPU Dominance: When CPUs Outperform for On-Device LLM Inference","created":"2025-05-09","cited_by_count":3,"area":null},{"id":"2505.15863","title":"Generative AI for Autonomous Driving: A Review","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2601.03181","title":"Multi-Modal Data-Enhanced Foundation Models for Prediction and Control in Wireless Networks: A Survey","created":"2026-01-06","cited_by_count":3,"area":null},{"id":"2410.01098","title":"Exploring Gen-AI applications in building research and industry: A review","created":"2024-10-01","cited_by_count":2,"area":null},{"id":"2412.14708","title":"Creation of AI-driven Smart Spaces for Enhanced Indoor Environments -- A Survey","created":"2024-12-19","cited_by_count":2,"area":null},{"id":"2501.15544","title":"Advancing Generative Artificial Intelligence and Large Language Models for Demand Side Management with Internet of Electric Vehicles","created":"2025-01-26","cited_by_count":2,"area":null},{"id":"2503.06029","title":"SmartBench: Is Your LLM Truly a Good Chinese Smartphone Assistant?","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2508.09035","title":"P/D-Device: Disaggregated Large Language Model between Cloud and Devices","created":"2025-08-12","cited_by_count":2,"area":null},{"id":"2510.01439","title":"Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2510.13848","title":"On-device System of Compositional Multi-tasking in Large Language Models","created":"2025-10-11","cited_by_count":2,"area":null},{"id":"2602.00166","title":"Joint Continual Learning of Local Language Models and Cloud Offloading Decisions with Budget Constraints","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2607.05476","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2501.10187","title":"Good things come in small packages: Should we build AI clusters with Lite-GPUs?","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2505.15030","title":"A Systematic Evaluation of On-Device LLMs: Quantization, Performance, and Resources","created":"2025-05-21","cited_by_count":1,"area":null},{"id":"2509.02411","title":"A Survey: Towards Privacy and Security in Mobile Large Language Models","created":"2025-09-02","cited_by_count":1,"area":null},{"id":"2509.06326","title":"AttestLLM: Efficient Attestation Framework for Billion-scale On-device LLMs","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2509.10682","title":"LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems","created":"2025-09-12","cited_by_count":1,"area":null},{"id":"2509.12423","title":"Small Models, Big Results: Achieving Superior Intent Extraction through Decomposition","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2510.25784","title":"zFLoRA: Zero-Latency Fused Low-Rank Adapters","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2607.15232","title":"In-Place Tokenizer Expansion for Pre-trained LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2503.21674","title":"Intelligent IoT Attack Detection Design via ODLLM with Feature Ranking-based Knowledge Base","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2505.14992","title":"Effective and Efficient Schema-aware Information Extraction Using On-Device Large Language Models","created":"2025-05-21","cited_by_count":0,"area":null},{"id":"2506.07695","title":"Towards a Small Language Model Lifecycle Framework","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2509.12994","title":"SitLLM: Large Language Models for Sitting Posture Health Understanding via Pressure Sensor Data","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2509.17477","title":"LingoQ: Bridging the Gap between EFL Learning and Work through AI-Generated Work-Related Quizzes","created":"2025-09-22","cited_by_count":0,"area":null},{"id":"2509.21192","title":"GEP: A GCG-Based method for extracting personally identifiable information from chatbots built on small language models","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2601.02641","title":"An Empirical Study of On-Device Translation for Real-Time Live-Stream Chat on Mobile Devices","created":"2026-01-06","cited_by_count":0,"area":null},{"id":"2601.09306","title":"On-Device Large Language Models for Sequential Recommendation","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2604.00039","title":"Transformers for Program Termination","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2604.05856","title":"Neural Network Pruning via QUBO Optimization","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2605.24411","title":"The Model Is Not the Product: A Dual-Pillar Architecture for Local-First Psychological Coaching","created":"2026-05-23","cited_by_count":0,"area":null},{"id":"2606.23370","title":"FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.20481","title":"Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.20806","title":"Profiling Lightweight Large Language Models","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2607.21602","title":"Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2607.21624","title":"FBLayout: Optimizing Memory Layout for Efficient LLM Finetuning on Mobile GPUs","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2608.20868","title":"Identify, Locate, Link: End-to-End Key-Value Extraction from Document Images","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2608.21172","title":"Thermo-FL: Thermal-Aware Robust Federated Fine-Tuning of Large Language Models for Edge AI","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.00005","title":"Incremental Risk Assessment of Progressive Elder Financial Scams via Instruction-Tuned Small Language Models","created":"2026-07-11","cited_by_count":0,"area":null},{"id":"2609.37454","title":"Governing the Edge: Automating Commercial Property and Casualty Insurance Underwriting via a Hybrid Local-Cloud Multi-Agent Framework","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}