{"total":18,"rows":[{"id":"2307.02973","title":"Pruning vs Quantization: Which is Better?","created":"2023-07-06","cited_by_count":46,"area":null},{"id":"2408.01803","title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs","created":"2024-08-03","cited_by_count":31,"area":null},{"id":"2405.20935","title":"Effective Interplay between Sparsity and Quantization: From Theory to Practice","created":"2024-05-31","cited_by_count":19,"area":null},{"id":"2502.16638","title":"Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression","created":"2025-02-23","cited_by_count":14,"area":null},{"id":"2410.13056","title":"Channel-Wise Mixed-Precision Quantization for Large Language Models","created":"2024-10-16","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":"2208.06064","title":"Mixed-Precision Neural Networks: A Survey","created":"2022-08-11","cited_by_count":7,"area":null},{"id":"2502.01705","title":"Progressive Binarization with Semi-Structured Pruning for LLMs","created":"2025-02-03","cited_by_count":5,"area":null},{"id":"2302.07612","title":"Towards Optimal Compression: Joint Pruning and Quantization","created":"2023-02-15","cited_by_count":4,"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":"2404.08010","title":"Differentiable Search for Finding Optimal Quantization Strategy","created":"2024-04-10","cited_by_count":2,"area":null},{"id":"2505.16332","title":"Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2306.01526","title":"Group channel pruning and spatial attention distilling for object detection","created":"2023-06-02","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":"2510.02822","title":"FlexiQ: Adaptive Mixed-Precision Quantization for Latency/Accuracy Trade-Offs in Deep Neural Networks","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2509.12363","title":"Enhancing Smart Farming Through Federated Learning: A Secure, Scalable, and Efficient Approach for AI-Driven Agriculture","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2510.09696","title":"Vanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2510.14463","title":"Pruning Overparameterized Multi-Task Networks for Degraded Web Image Restoration","created":"2025-10-16","cited_by_count":0,"area":null}],"next_cursor":null}