{"total":21,"rows":[{"id":"2312.03863","title":"Efficient Large Language Models: A Survey","created":"2023-12-06","cited_by_count":186,"area":null},{"id":"2409.15790","title":"Small Language Models: Survey, Measurements, and Insights","created":"2024-09-24","cited_by_count":112,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2312.06786","title":"Mixture-of-Linear-Experts for Long-term Time Series Forecasting","created":"2023-12-11","cited_by_count":29,"area":null},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2505.01821","title":"Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Survey","created":"2025-05-03","cited_by_count":14,"area":null},{"id":"2401.01923","title":"The Internet of Things in the Era of Generative AI: Vision and Challenges","created":"2024-01-03","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2505.09214","title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","created":"2025-05-14","cited_by_count":7,"area":null},{"id":"2408.10230","title":"A General-Purpose Device for Interaction with LLMs","created":"2024-08-02","cited_by_count":3,"area":null},{"id":"2410.10181","title":"Scalable Multi-Domain Adaptation of Language Models using Modular Experts","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2506.19884","title":"MNN-AECS: Energy Optimization for LLM Decoding on Mobile Devices via Adaptive Core Selection","created":"2025-06-24","cited_by_count":3,"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":"2402.12061","title":"All Language Models Large and Small","created":"2024-02-19","cited_by_count":1,"area":null},{"id":"2402.16848","title":"InterroGate: Learning to Share, Specialize, and Prune Representations for Multi-task Learning","created":"2024-02-26","cited_by_count":1,"area":null},{"id":"2602.13052","title":"Quantization-Aware Collaborative Inference for Large Embodied AI Models","created":"2026-02-13","cited_by_count":1,"area":null},{"id":"2602.23312","title":"Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2609.04238","title":"Budgeting Bytes: A Windowed Storage Roofline and Dual-Budget Architecture Ablations for Storage-Bound LLM Decoding","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.23582","title":"ARID: A Deployable Edge AI System for Structured Information Extraction from Industrial Maintenance Work Orders","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.06387","title":"Scaling Down the Scaling Laws: Parameter Efficiency and Compute-Optimal Training in Resource-Constrained Large Language Models","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}