{"total":14,"rows":[{"id":"2208.07339","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","created":"2022-08-15","cited_by_count":906,"area":null},{"id":"2402.09748","title":"Model Compression and Efficient Inference for Large Language Models: A Survey","created":"2024-02-15","cited_by_count":64,"area":null},{"id":"2402.05964","title":"A Survey on Transformer Compression","created":"2024-02-05","cited_by_count":46,"area":null},{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2211.09718","title":"Numerical Optimizations for Weighted Low-rank Estimation on Language Model","created":"2022-11-02","cited_by_count":14,"area":null},{"id":"2307.12659","title":"A Model for Every User and Budget: Label-Free and Personalized Mixed-Precision Quantization","created":"2023-07-24","cited_by_count":8,"area":null},{"id":"2502.16767","title":"A Hybrid Approach to Information Retrieval and Answer Generation for Regulatory Texts","created":"2025-02-24","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":"2308.03290","title":"FLIQS: One-Shot Mixed-Precision Floating-Point and Integer Quantization Search","created":"2023-08-07","cited_by_count":6,"area":null},{"id":"2501.03643","title":"Effective and Efficient Mixed Precision Quantization of Speech Foundation Models","created":"2025-01-07","cited_by_count":5,"area":null},{"id":"2312.13301","title":"SimQ-NAS: Simultaneous Quantization Policy and Neural Architecture Search","created":"2023-12-19","cited_by_count":2,"area":null},{"id":"2403.05365","title":"The Impact of Quantization on the Robustness of Transformer-based Text Classifiers","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2510.21086","title":"DictPFL: Efficient and Private Federated Learning on Encrypted Gradients","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2512.00829","title":"Accelerating Bangla NLP Tasks with Automatic Mixed Precision: Resource-Efficient Training Preserving Model Efficacy","created":"2025-11-30","cited_by_count":0,"area":null}],"next_cursor":null}