{"total":17,"rows":[{"id":"2311.05804","title":"Model-as-a-Service (MaaS): A Survey","created":"2023-11-10","cited_by_count":25,"area":null},{"id":"2412.04782","title":"A Survey of Sustainability in Large Language Models: Applications, Economics, and Challenges","created":"2024-12-06","cited_by_count":18,"area":null},{"id":"2304.14271","title":"A Survey on Approximate Edge AI for Energy Efficient Autonomous Driving Services","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2305.19549","title":"Accurate and Structured Pruning for Efficient Automatic Speech Recognition","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2312.15322","title":"Hardware-Aware DNN Compression via Diverse Pruning and Mixed-Precision Quantization","created":"2023-12-23","cited_by_count":10,"area":null},{"id":"2206.15408","title":"Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition","created":"2022-06-30","cited_by_count":5,"area":null},{"id":"2603.18426","title":"Prune-then-Quantize or Quantize-then-Prune? Understanding the Impact of Compression Order in Joint Model Compression","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2408.13925","title":"Infrared Domain Adaptation with Zero-Shot Quantization","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2411.00907","title":"On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performance","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2506.13180","title":"Dynamic Acoustic Model Architecture Optimization in Training for ASR","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2604.04988","title":"Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2110.04378","title":"Performance optimizations on deep noise suppression models","created":"2021-10-08","cited_by_count":0,"area":null},{"id":"2404.10003","title":"Lightweight Geometric Deep Learning for Molecular Modelling in Catalyst Discovery","created":"2024-04-05","cited_by_count":0,"area":null},{"id":"2507.10059","title":"GeLaCo: An Evolutionary Approach to Layer Compression","created":"2025-07-14","cited_by_count":0,"area":null},{"id":"2508.15883","title":"Beyond Imaging: Vision Transformer Digital Twin Surrogates for 3D+T Biological Tissue Dynamics","created":"2025-08-21","cited_by_count":0,"area":null},{"id":"2509.04244","title":"Integrating Pruning with Quantization for Efficient Deep Neural Networks Compression","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.18193","title":"TinyEcoWeedNet: Edge Efficient Real-Time Aerial Agricultural Weed Detection","created":"2025-09-19","cited_by_count":0,"area":null}],"next_cursor":null}