{"total":104,"rows":[{"id":"2411.18279","title":"Large Language Model-Brained GUI Agents: A Survey","created":"2024-11-27","cited_by_count":162,"area":"agents"},{"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":"2412.18116","title":"AutoDroid-V2: Boosting SLM-based GUI Agents via Code Generation","created":"2024-12-24","cited_by_count":34,"area":"agents"},{"id":"2606.15912","title":"On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents","created":"2026-06-14","cited_by_count":27,"area":"distill"},{"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,"area":"lr"},{"id":"2605.07725","title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","created":"2026-05-08","cited_by_count":21,"area":"agents"},{"id":"2411.06681","title":"WDMoE: Wireless Distributed Mixture of Experts for Large Language Models","created":"2024-11-11","cited_by_count":12,"area":"moe"},{"id":"2506.24045","title":"Agent.xpu: Efficient Scheduling of Agentic LLM Workloads on Heterogeneous SoC","created":"2025-06-30","cited_by_count":11,"area":"agents"},{"id":"2512.10371","title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2501.03265","title":"Cognitive Edge Computing: A Comprehensive Survey on Optimizing Large Models and AI Agents for Pervasive Deployment","created":"2025-01-04","cited_by_count":10,"area":"lr"},{"id":"2503.16585","title":"Distributed LLMs and Multimodal Large Language Models: A Survey on Advances, Challenges, and Future Directions","created":"2025-03-20","cited_by_count":10,"area":"mllm"},{"id":"2509.11961","title":"Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding","created":"2025-09-15","cited_by_count":9,"area":"lr"},{"id":"2606.25115","title":"Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory","created":"2026-06-23","cited_by_count":9,"area":"agents"},{"id":"2410.08014","title":"Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2507.06567","title":"SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference","created":"2025-07-09","cited_by_count":7,"area":"moe"},{"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":"2509.24050","title":"Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training","created":"2025-09-28","cited_by_count":5,"area":"lr"},{"id":"2510.16034","title":"Disaster Management in the Era of Agentic AI Systems: A Vision for Collective Human-Machine Intelligence for Augmented Resilience","created":"2025-10-16","cited_by_count":5,"area":"agents"},{"id":"2604.25975","title":"Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective","created":"2026-04-28","cited_by_count":5,"area":"lr"},{"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":"2510.02657","title":"Less LLM, More Documents: Searching for Improved RAG","created":"2025-10-03","cited_by_count":4,"area":"rag"},{"id":"2510.09354","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-10-10","cited_by_count":4,"area":"lr"},{"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":"2605.03804","title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","created":"2026-05-05","cited_by_count":3,"area":"agents"},{"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":"2507.12759","title":"Logit Arithmetic Elicits Long Reasoning Capabilities Without Training","created":"2025-07-17","cited_by_count":2,"area":"lr"},{"id":"2507.18454","title":"Sandwich: Joint Configuration Search and Hot-Switching for Efficient CPU LLM Serving","created":"2025-05-19","cited_by_count":2,"area":"inference"},{"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":"2602.00603","title":"Direct Preference Optimization with Rating Information: Practical Algorithms and Provable Gains","created":"2026-01-31","cited_by_count":2,"area":"alignment"},{"id":"2603.19172","title":"DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge","created":"2026-03-19","cited_by_count":2,"area":"moe"},{"id":"2607.05476","title":"Parameter-Free Encoders Remain Viable for RDB Foundation Models","created":"2026-07-06","cited_by_count":2,"area":null},{"id":"2607.26865","title":"Think Short, Defer Smart, Act, and Repeat: Calibrated Reasoning and Uncertainty-Aware Deferral for Edge LLM Agents","created":"2026-07-29","cited_by_count":2,"area":"lr"},{"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":"2508.10019","title":"Decoupling Understanding from Reasoning via Problem Space Mapping for Small-Scale Model Reasoning","created":"2025-08-07","cited_by_count":1,"area":"lr"},{"id":"2509.01551","title":"Cloud-Device Collaborative Agents for Sequential Recommendation","created":"2025-09-01","cited_by_count":1,"area":"lr"},{"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":"2509.10561","title":"AVEC: Bootstrapping Privacy for Local LLMs","created":"2025-09-10","cited_by_count":1,"area":"synth"},{"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":"2512.03608","title":"KVNAND: Efficient On-Device Large Language Model Inference Using DRAM-Free In-Flash Computing","created":"2025-12-03","cited_by_count":1,"area":"inference"},{"id":"2601.17569","title":"Improving User Privacy in Personalized Generation: Client-Side Retrieval-Augmented Modification of Server-Side Generated Speculations","created":"2026-01-24","cited_by_count":1,"area":"rag"},{"id":"2603.09046","title":"FlexServe: A Fast and Secure LLM Serving System for Mobile Devices with Flexible Resource Isolation","created":"2026-03-10","cited_by_count":1,"area":"inference"},{"id":"2604.17701","title":"WISV: Wireless-Informed Semantic Verification for Distributed Speculative Decoding in Device-Edge LLM Inference","created":"2026-04-20","cited_by_count":1,"area":"inference"},{"id":"2605.18535","title":"Beyond Scaling: Agents Are Heading to the Edge","created":"2026-05-18","cited_by_count":1,"area":"agents"},{"id":"2606.11257","title":"Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite","created":"2026-06-09","cited_by_count":1,"area":"rag"},{"id":"2607.15232","title":"In-Place Tokenizer Expansion for Pre-trained LLMs","created":"2026-07-16","cited_by_count":1,"area":null},{"id":"2502.05291","title":"Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet","created":"2025-02-07","cited_by_count":0,"area":"safety"},{"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":"2507.20650","title":"Hot-Swap MarkBoard: An Efficient Black-box Watermarking Approach for Large-scale Model Distribution","created":"2025-07-28","cited_by_count":0,"area":"safety"},{"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":"2510.03913","title":"PsycholexTherapy: Simulating Reasoning in Psychotherapy with Small Language Models in Persian","created":"2025-10-04","cited_by_count":0,"area":"lr"},{"id":"2510.19670","title":"CoSense-LLM: Semantics at the Edge with Cost- and Uncertainty-Aware Cloud-Edge Cooperation","created":"2025-10-22","cited_by_count":0,"area":"inference"},{"id":"2512.15787","title":"Toward Agentic Environments: GenAI and the Convergence of AI, Sustainability, and Human-Centric Spaces","created":"2025-12-15","cited_by_count":0,"area":"agents"},{"id":"2512.23029","title":"Viability and Performance of a Private LLM Server for SMBs: A Benchmark Analysis of Qwen3-30B on Consumer-Grade Hardware","created":"2025-12-28","cited_by_count":0,"area":"moe"},{"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":"2601.20041","title":"CiMRAG: CiM-Aware Domain-Adaptive and Noise-Resilient Retrieval-Augmented Generation for Edge-Based LLMs","created":"2026-01-27","cited_by_count":0,"area":"rag"},{"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":"2604.06562","title":"On Emotion-Sensitive Decision Making of Small Language Model Agents","created":"2026-04-08","cited_by_count":0,"area":"agents"},{"id":"2604.17459","title":"Transparent and Controllable Recommendation Filtering via Multimodal Multi-Agent Collaboration","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2604.17817","title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","created":"2026-04-20","cited_by_count":0,"area":"agents"},{"id":"2604.23941","title":"GoClick: Lightweight Element Grounding Model for Autonomous GUI Interaction","created":"2026-04-27","cited_by_count":0,"area":"agents"},{"id":"2605.18831","title":"Towards Discovery of Polymers for Insulin Delivery via Physics-Grounded Agentic Workflows","created":"2026-05-12","cited_by_count":0,"area":"agents"},{"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":"2607.11423","title":"ToFu: A White-Box, Token-Efficient Agent Harness for Researchers","created":"2026-07-13","cited_by_count":0,"area":"agents"},{"id":"2607.16431","title":"RIMS: Preference Optimization via Smoothed Multi-pair Aggregation for Small-Scale LLM Retrieval-Augmented Generation","created":"2026-07-17","cited_by_count":0,"area":"rag"},{"id":"2607.18819","title":"In-Context Learning for Wound Classification with Small Multimodal Language Models","created":"2026-07-21","cited_by_count":0,"area":"mllm"},{"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":"2608.19535","title":"From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG","created":"2026-08-20","cited_by_count":0,"area":"rag"},{"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}],"next_cursor":"100"}