FRM-PTQ: Feature relationship matching enhanced low-bit post-training quantization for large language models
- 17 January 2026
- journal article
- Published by Elsevier in Neural Networks
- Vol. 198, 108619
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62306084)
- National Natural Science Foundation of China (U23B2051)
- Shenzhen Science and Technology Innovation Program
- Science, Technology and Innovation Commission of Shenzhen Municipality (ZDSYS20230626091203008)
- Science, Technology and Innovation Commission of Shenzhen Municipality (KJZD20230923115113026)
- Science, Technology and Innovation Commission of Shenzhen Municipality (GXWD20231128102243003)
This publication has 11 references indexed in Scilit:
- A survey of low-bit large language models: Basics, systems, and algorithmsNeural Networks, 2025
- PT-BitNet: Scaling up the 1-Bit large language model with post-training quantizationNeural Networks, 2025
- Emotion-Aware Embedding Fusion in Large Language Models (Flan-T5, Llama 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response GenerationAI, 2025
- Enhancing Economic Growth Time Series for UAE Forecasting with Deep Learning: A Seq2Seq and Attention-Driven LSTM ApproachEDRAAK, 2025
- Integrating Machine Learning and Genetic Algorithms to Enhance Gene-Disease Classification: An XBNet-Based FrameworkBabylonian Journal of Machine Learning, 2025
- Generative Models in Natural Language Processing: A Comparative Study of ChatGPT and GeminiBabylonian Journal of Artificial Intelligence, 2024
- A Brief Review on Preprocessing Text in Arabic Language Dataset: Techniques and ChallengesBabylonian Journal of Artificial Intelligence, 2024
- Does Lack of Knowledge and Hardship of Information Access Signify Powerful AI? A Large Language Model PerspectiveApplied Data Science and Analysis, 2023
- Blockwise compression of transformer-based models without retrainingNeural Networks, 2023
- Interpretation of the Kurtosis StatisticThe American Statistician, 1970