arXiv subjects

Xiaoman Liu

Publications and source records attributed to Xiaoman Liu.

3 recordsLinked to original sources

arXiv2025

Towards Adaptive Memory-Based Optimization for Enhanced Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG), by integrating non-parametric knowledge from external knowledge bases into models, has emerged as a promising approach to enhancing response accuracy while mitigating factual errors and hallucinations. This method has been widely applied in tasks such as Question Answering (QA). However, existing RAG methods struggle with open-domain QA tasks because they perform independent retrieval operations and directly incorporate the retrieved information into generation without maintaining a summarizing memory or using adaptive retrieval strategies, leading to noise from redundant information and insufficient information integration. To address these challenges, we propose Adaptive memory-based optimization for enhanced RAG (Amber) for open-domain QA tasks, which comprises an Agent-based Memory Updater, an Adaptive Information Collector, and a Multi-granular Content Filter, working together within an iterative memory updating paradigm. Specifically, Amber integrates and optimizes the language model's memory through a multi-agent collaborative approach, ensuring comprehensive knowledge integration from previous retrieval steps. It dynamically adjusts retrieval queries and decides when to stop retrieval based on the accumulated knowledge, enhancing retrieval efficiency and effectiveness. Additionally, it reduces noise by filtering irrelevant content at multiple levels, retaining essential information to improve overall model performance. We conduct extensive experiments on several open-domain QA datasets, and the results demonstrate the superiority and effectiveness of our method and its components. The source code is available \footnote{https://anonymous.4open.science/r/Amber-B203/}.

cs.IR↗

arXiv2024

Towards CPU Performance Prediction: New Challenge Benchmark Dataset and Novel Approach

The server central processing unit (CPU) market continues to exhibit robust demand due to the rising global need for computing power. Against this backdrop, CPU benchmark performance prediction is crucial for architecture designers. It offers profound insights for optimizing system designs and significantly reduces the time required for benchmark testing. However, the current research suffers from a lack of a unified, standard and a comprehensive dataset covering various CPU benchmark suites on real machines. Additionally, the traditional simulation-based methods suffer from slow simulation speeds. Furthermore, traditional machine learning approaches not only struggle to process complex features across various hardware configurations but also fall short in achieving sufficient accuracy. To bridge these gaps, we firstly perform a streamlined data preprocessing and reorganize our in-house datasets gathered from a variety CPU models of 4th Generation Intel Xeon Scalable Processors on various benchmark suites. We then propose Nova CPU Performance Predictor (NCPP), a deep learning model with attention mechanisms, specifically designed to predict CPU performance across various benchmarks. Our model effectively captures key hardware configurations affecting performance in across various benchmarks. Moreover, we compare eight mainstream machine learning methods, demonstrating the significant advantages of our model in terms of accuracy and explainability over existing approaches. Finally, our results provide new perspectives and practical strategies for hardware designers. To foster further research and collaboration, we \textit{\textbf{open-source}} the model \url{https://github.com/xiaoman-liu/NCPP}

cs.PF↗

arXiv2024

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Forecasting CPU performance, which involves estimating performance scores based on hardware characteristics during operation, is crucial for computational system design and resource management. This research field currently faces two primary challenges. First, the diversity of CPU products and the specialized nature of hardware characteristics make real-world data collection difficult. Second, existing approaches, whether reliant on hardware simulation models or machine learning, suffer from significant drawbacks, such as lengthy simulation cycles, low prediction accuracy, and neglect of characteristic correlations. To address these issues, we first gathered, preprocessed, and standardized historical data from the 4th Generation Intel Xeon Scalable Processors across various benchmark suites to create a new dataset named PerfCastDB. Subsequently, we developed a novel network, MambaCPU (MaC), as the baseline model for the PerfCastDB dataset. This model employs the mamba structure to explore global dependencies and correlations among multiple characteristics. The use of intra- and inter-group attention mechanisms further refines correlations within and between characteristic groups. These techniques enhance MaC's capability to analyze and mine complex multivariate correlations. Comparative experiments on the PerfCastDB dataset demonstrate that MaC surpasses existing methods, confirming its effectiveness. Additionally, we have open-sourced part of the dataset and the MaC code at \url{https://github.com/xiaoman-liu/MaC} to facilitate further research.

cs.PF↗