arXiv subjects

Ming Xia

Publications and source records attributed to Ming Xia.

6 recordsLinked to original sources

arXiv2026

Unleash the Potential of Long Semantic IDs for Generative Recommendation

Semantic ID-based generative recommenders face a granularity-efficiency dilemma between efficient recommendation with short IDs and expressive item modeling with long IDs. To break this dilemma, we propose ACERec, a framework that preserves the semantic richness of long IDs while keeping the recommendation process efficient. Concretely, ACERec employs an Attentive Token Merger to compress long semantic IDs into compact yet faithful latent tokens. To better capture user intent from the compressed semantics, we further introduce a dedicated Intent Token, optimized by a dual-granularity objective that combines token-level generation with item-level intent-semantic alignment. Extensive experiments on nine real-world benchmarks show that ACERec consistently outperforms state-of-the-art methods, yielding average relative improvements of 12.92% in NDCG@10 and 7.49% in Recall@10 over the strongest baselines.

cs.IR↗

arXiv2025

CT-CFAR A Robust CFAR Detector Based on CLEAN and Truncated Statistics in Sidelobe-Contaminated Environments

This paper proposes a constant false alarm rate (CFAR) target detection algorithm based on the CLEAN concept and truncated statistics to mitigate the non-homogeneity of reference samples caused by sidelobe contamination and other abnormal interferences within the reference window. The proposed algorithm employs truncated statistics to separate target and noise components in the radar echo power spectrum, thereby restoring the homogeneity assumption of the reference window. In addition, learnable historical sidelobe information is introduced to enhance the robustness and environmental adaptability of the detection process. Furthermore, based on multichannel echo data, a target reconstruction model that combines the Candan algorithm with least-squares estimation is established, incorporating the CLEAN concept to suppress sidelobe interference. Monte Carlo simulations and real-world measurement experiments demonstrate that the proposed CT-CFAR algorithm achieves high-precision target detection without requiring prior knowledge of abnormal samples. Compared with various CFAR algorithms, the proposed approach overcomes the limitations of the reference window, accurately estimates the noise spectrum, and exhibits superior detection performance and computational efficiency in complex scenarios affected by sidelobe contamination.

eess.SP↗

arXiv2022

Rethinking Gradient Operator for Exposing AI-enabled Face Forgeries

For image forensics, convolutional neural networks (CNNs) tend to learn content features rather than subtle manipulation traces, which limits forensic performance. Existing methods predominantly solve the above challenges by following a general pipeline, that is, subtracting the original pixel value from the predicted pixel value to make CNNs pay attention to the manipulation traces. However, due to the complicated learning mechanism, these methods may bring some unnecessary performance losses. In this work, we rethink the advantages of gradient operator in exposing face forgery, and design two plug-and-play modules by combining gradient operator with CNNs, namely tensor pre-processing (TP) and manipulation trace attention (MTA) module. Specifically, TP module refines the feature tensor of each channel in the network by gradient operator to highlight the manipulation traces and improve the feature representation. Moreover, MTA module considers two dimensions, namely channel and manipulation traces, to force the network to learn the distribution of manipulation traces. These two modules can be seamlessly integrated into CNNs for end-to-end training. Experiments show that the proposed network achieves better results than prior works on five public datasets. Especially, TP module greatly improves the accuracy by at least 4.60% compared with the existing pre-processing module only via simple tensor refinement. The code is available at: https://github.com/EricGzq/GocNet-pytorch.

cs.CV↗

arXiv2021

Federated Ensemble Model-based Reinforcement Learning in Edge Computing

Federated learning (FL) is a privacy-preserving distributed machine learning paradigm that enables collaborative training among geographically distributed and heterogeneous devices without gathering their data. Extending FL beyond the supervised learning models, federated reinforcement learning (FRL) was proposed to handle sequential decision-making problems in edge computing systems. However, the existing FRL algorithms directly combine model-free RL with FL, thus often leading to high sample complexity and lacking theoretical guarantees. To address the challenges, we propose a novel FRL algorithm that effectively incorporates model-based RL and ensemble knowledge distillation into FL for the first time. Specifically, we utilise FL and knowledge distillation to create an ensemble of dynamics models for clients, and then train the policy by solely using the ensemble model without interacting with the environment. Furthermore, we theoretically prove that the monotonic improvement of the proposed algorithm is guaranteed. The extensive experimental results demonstrate that our algorithm obtains much higher sample efficiency compared to classic model-free FRL algorithms in the challenging continuous control benchmark environments under edge computing settings. The results also highlight the significant impact of heterogeneous client data and local model update steps on the performance of FRL, validating the insights obtained from our theoretical analysis.

cs.LG↗

arXiv2018

2D materials coated plasmonic structures for SERS applications

Two-dimensional (2D) materials, such as graphene and hexagonal boron nitride, are new kind of materials that can serve as substrates for surface enhanced Raman spectroscopy (SERS). When combined with traditional metallic plasmonic structures, the hybrid 2D materials/metal SERS platform brings extra benefits, including higher SERS enhancement factors, oxidation protection of metal surface, and protection of molecules from photo-induced damage. This perspective gives an overview of recent progress in 2D materials coated plasmonic structure in SERS application. This paper focuses on the fabrication of the hybrid 2D materials/metal SERS platform and their applications for Raman enhancement.

cond-mat.mtrl-sci↗

arXiv2017

A review on applications of two-dimensional materials in surface enhanced Raman spectroscopy

Two-dimensional (2D) materials, such as graphene and MoS2, have been attracting wide interest in surface enhancement Raman spectroscopy. This perspective gives an overview of recent developments in 2D materials' application in surface enhanced Raman spectroscopy. This review focuses on the applications of using bare 2D materials and metal/2D material hybrid substrate for Raman enhancement. The Raman enhancing mechanism of 2D materials will also be discussed. The progress covered herein shows great promise for widespread adoption of 2D materials in SERS application.

cond-mat.mtrl-sci↗