{"total":27,"rows":[{"id":"2506.09397","title":"SLED: A Speculative LLM Decoding Framework for Efficient Edge Serving","created":"2025-06-11","cited_by_count":13,"area":null},{"id":"2506.09104","title":"Unifying Block-wise PTQ and Distillation-based QAT for Progressive Quantization toward 2-bit Instruction-Tuned LLMs","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2601.22362","title":"Understanding Efficiency: Quantization, Batching, and Serving Strategies in LLM Energy Use","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2607.08734","title":"The Illusion of Equivalency: Statistical Characterization of Quantization Effects in LLMs","created":"2026-07-09","cited_by_count":4,"area":null},{"id":"2505.06907","title":"A Survey on Foundation Models for Personalized Federated Intelligence","created":"2025-05-11","cited_by_count":3,"area":null},{"id":"2509.04534","title":"Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation","created":"2025-09-04","cited_by_count":3,"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":"2605.08137","title":"Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI","created":"2026-05-02","cited_by_count":2,"area":null},{"id":"2605.20706","title":"Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2609.05881","title":"Broken on Arrival: Silently Defective LLM Artifacts in Public Model Registries and How to Catch Them","created":"2026-09-05","cited_by_count":2,"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":"2509.26124","title":"Vocabulary Customization for Efficient Domain-Specific LLM Deployment","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2602.01027","title":"SFMP: Fine-Grained, Hardware-Friendly and Search-Free Mixed-Precision Quantization for Large Language Models","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2607.09172","title":"Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2608.25053","title":"Hydra: Phase-Aware Workload Characterization of LLM Inference across Edge SoC Generations, Backends, and Quantization Levels","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2510.17885","title":"Metrics and evaluations for computational and sustainable AI efficiency","created":"2025-10-18","cited_by_count":0,"area":null},{"id":"2603.23668","title":"Energy Efficient Software Hardware CoDesign for Machine Learning: From TinyML to Large Language Models","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2605.03111","title":"Benchmarking Local Language Models for Social Robots using Edge Devices","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2606.17489","title":"Online LLM Selection via Constrained Bandits with Time-Varying Demand","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2608.02031","title":"Learning-Based Collaborative MEC for LLM Inference with Soft-Deadline Awareness via Transformer-Enhanced PPO","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.09291","title":"UnionSparse: An Index-Efficient Sparsity Framework for Low-Bit Sparse LLM Inference on Edge","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.16391","title":"Ventor-QTest: Threat-Model-Driven Verification of Vendor-Hosted LLM APIs","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.28667","title":"GreenBench: Benchmarking Energy Efficiency and Carbon Footprint of Open-Source LLM Inference on Apple Silicon","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.00665","title":"Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.11940","title":"The Battery Price of edge AI: A study of the Environmental Impact of LLM Inference on Mobile Devices","created":"2026-07-10","cited_by_count":0,"area":null},{"id":"2609.25014","title":"Not All 4-bit Quantizers Are Equal: Deployment-Time Mitigation of PII Leakage in Fine-Tuned Small Language Models","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}