arXiv subjects

Xiaoxu Guo

Publications and source records attributed to Xiaoxu Guo.

3 recordsLinked to original sources

arXiv2025

Multimodal Fine-grained Reasoning for Post Quality Evaluation

Accurately assessing post quality requires complex relational reasoning to capture nuanced topic-post relationships. However, existing studies face three major limitations: (1) treating the task as unimodal categorization, which fails to leverage multimodal cues and fine-grained quality distinctions; (2) introducing noise during deep multimodal fusion, leading to misleading signals; and (3) lacking the ability to capture complex semantic relationships like relevance and comprehensiveness. To address these issues, we propose the Multimodal Fine-grained Topic-post Relational Reasoning (MFTRR) framework, which mimics human cognitive processes. MFTRR reframes post-quality assessment as a ranking task and incorporates multimodal data to better capture quality variations. It consists of two key modules: (1) the Local-Global Semantic Correlation Reasoning Module, which models fine-grained semantic interactions between posts and topics at both local and global levels, enhanced by a maximum information fusion mechanism to suppress noise; and (2) the Multi-Level Evidential Relational Reasoning Module, which explores macro- and micro-level relational cues to strengthen evidence-based reasoning. We evaluate MFTRR on three newly constructed multimodal topic-post datasets and the public Lazada-Home dataset. Experimental results demonstrate that MFTRR significantly outperforms state-of-the-art baselines, achieving up to 9.52% NDCG@3 improvement over the best unimodal method on the Art History dataset.

cs.LG↗

arXiv2019

Quasi-Spin Ising Model and Monte Carlo Simulation of Ferroelastic Phase Transition: 3D Diffuse Scattering and Displacement Short-Range Ordering in Pre-Martensitic State

A quasi-spin Ising model of ferroelastic phase transition is developed and employed to perform atomic-scale Monte Carlo simulation of thermoelastic martensitic transformation. The quasi-spin variable associated with the lattice sites characterizes the local unit cells of the orientation variants of the ground-state martensite phase, which interact with each other through long-range elastic interactions. The simulation study focuses on the intrinsic behaviors of a defect-free crystal that undergoes cubic-to-tetragonal martensitic transformation. It is shown that the diffuse scattering in the pre-martensitic austenite state results from the spatial correlation of the atomic-scale heterogeneous lattice displacements and manifests the displacement short-range ordering. The effects of temperature, elastic anisotropy, and shear modulus softening on the diffuse scattering and displacement short-range ordering are investigated. It is found that elastic softening in the shear modulus C'=(C11-C12)/2 promotes <110>|<1-10> displacement plane waves that stabilize the cubic austenite phase through increased entropy, decreasing the martensitic transformation temperature. The simulated diffuse scattering is compared and agrees with the complementary synchrotron X-ray single-crystal diffuse scattering experiment.

cond-mat.mtrl-sci↗

arXiv2019

LoadCNN: A Low Training Cost Deep Learning Model for Day-Ahead Individual Residential Load Forecasting

Accurate day-ahead individual residential load forecasting is of great importance to various applications of smart grid on day-ahead market. Deep learning, as a powerful machine learning technology, has shown great advantages and promising application in load forecasting tasks. However, deep learning is a computationally-hungry method, and requires high costs (e.g., time, energy and CO2 emission) to train a deep learning model, which aggravates the energy crisis and incurs a substantial burden to the environment. As a consequence, the deep learning methods are difficult to be popularized and applied in the real smart grid environment. In this paper, we propose a low training cost model based on convolutional neural network, namely LoadCNN, for next-day load forecasting of individual resident with reduced training cost. The experiments show that the training time of LoadCNN is only approximately 1/54 of the one of other state-of-the-art models, and energy consumption and CO2 emissions are only approximate 1/45 of those of other state-of-the-art models based on the same indicators. Meanwhile, the prediction accuracy of our model is equal to that of current state-of-the-art models, making LoadCNN the first load forecasting model simultaneously achieving high prediction accuracy and low training costs. LoadCNN is an efficient green model that is able to be quickly, cost-effectively and environmentally-friendly deployed in a realistic smart grid environment.

eess.SP↗