arXiv subjects

Hongbo Wang

Publications and source records attributed to Hongbo Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Characterization of silicon photomultipliers for their application in muon scattering tomography

Muon scattering tomography is a non-destructive technique used to image different materials by utilizing natural cosmic ray muons. Typically it requires position-sensitive detectors with a sub-millimeter resolution to effectively distinguish high-$Z$ materials in a compact system. The plastic scintillating fiber detector is a feasible candidate and is currently being designed with one-dimensional silicon photomultiplier (SiPM) readout. In this work, we constructed experimental setups to characterize three different SiPMs from the NDL, SensL, and HPK manufacturers for optimal performance of the scintillating fiber detector. The breakdown voltage, temperature compensation factor, dark noise, and photodetection efficiency of each SiPM are evaluated and summarized. Among the SiPMs tested, the HPK SiPM demonstrated the lowest dark count rate and crosstalk probability while exhibiting the best photodetection efficiency response at the emission wavelengths of the scintillating fibers. This makes the HPK SiPM particularly well-suited to meet the requirements of the detector and serves as a reference for further customization of the one-dimensional SiPM array.

physics.ins-det↗

arXiv2024

Task Adaptive Feature Distribution Based Network for Few-shot Fine-grained Target Classification

Metric-based few-shot fine-grained classification has shown promise due to its simplicity and efficiency. However, existing methods often overlook task-level special cases and struggle with accurate category description and irrelevant sample information. To tackle these, we propose TAFD-Net: a task adaptive feature distribution network. It features a task-adaptive component for embedding to capture task-level nuances, an asymmetric metric for calculating feature distribution similarities between query samples and support categories, and a contrastive measure strategy to boost performance. Extensive experiments have been conducted on three datasets and the experimental results show that our proposed algorithm outperforms recent incremental learning algorithms.

cs.CV↗

arXiv2024

Towards Comprehensive Detection of Chinese Harmful Memes

This paper has been accepted in the NeurIPS 2024 D & B Track. Harmful memes have proliferated on the Chinese Internet, while research on detecting Chinese harmful memes significantly lags behind due to the absence of reliable datasets and effective detectors. To this end, we focus on the comprehensive detection of Chinese harmful memes. We construct ToxiCN MM, the first Chinese harmful meme dataset, which consists of 12,000 samples with fine-grained annotations for various meme types. Additionally, we propose a baseline detector, Multimodal Knowledge Enhancement (MKE), incorporating contextual information of meme content generated by the LLM to enhance the understanding of Chinese memes. During the evaluation phase, we conduct extensive quantitative experiments and qualitative analyses on multiple baselines, including LLMs and our MKE. The experimental results indicate that detecting Chinese harmful memes is challenging for existing models while demonstrating the effectiveness of MKE. The resources for this paper are available at https://github.com/DUT-lujunyu/ToxiCN_MM.

cs.CL↗

arXiv2024

PclGPT: A Large Language Model for Patronizing and Condescending Language Detection

Disclaimer: Samples in this paper may be harmful and cause discomfort! Patronizing and condescending language (PCL) is a form of speech directed at vulnerable groups. As an essential branch of toxic language, this type of language exacerbates conflicts and confrontations among Internet communities and detrimentally impacts disadvantaged groups. Traditional pre-trained language models (PLMs) perform poorly in detecting PCL due to its implicit toxicity traits like hypocrisy and false sympathy. With the rise of large language models (LLMs), we can harness their rich emotional semantics to establish a paradigm for exploring implicit toxicity. In this paper, we introduce PclGPT, a comprehensive LLM benchmark designed specifically for PCL. We collect, annotate, and integrate the Pcl-PT/SFT dataset, and then develop a bilingual PclGPT-EN/CN model group through a comprehensive pre-training and supervised fine-tuning staircase process to facilitate implicit toxic detection. Group detection results and fine-grained detection from PclGPT and other models reveal significant variations in the degree of bias in PCL towards different vulnerable groups, necessitating increased societal attention to protect them.

cs.CL↗

arXiv2024

Towards Patronizing and Condescending Language in Chinese Videos: A Multimodal Dataset and Detector

Patronizing and Condescending Language (PCL) is a form of discriminatory toxic speech targeting vulnerable groups, threatening both online and offline safety. While toxic speech research has mainly focused on overt toxicity, such as hate speech, microaggressions in the form of PCL remain underexplored. Additionally, dominant groups' discriminatory facial expressions and attitudes toward vulnerable communities can be more impactful than verbal cues, yet these frame features are often overlooked. In this paper, we introduce the PCLMM dataset, the first Chinese multimodal dataset for PCL, consisting of 715 annotated videos from Bilibili, with high-quality PCL facial frame spans. We also propose the MultiPCL detector, featuring a facial expression detection module for PCL recognition, demonstrating the effectiveness of modality complementarity in this challenging task. Our work makes an important contribution to advancing microaggression detection within the domain of toxic speech.

cs.CV↗

arXiv2024

Rethinking Mutual Information for Language Conditioned Skill Discovery on Imitation Learning

Language-conditioned robot behavior plays a vital role in executing complex tasks by associating human commands or instructions with perception and actions. The ability to compose long-horizon tasks based on unconstrained language instructions necessitates the acquisition of a diverse set of general-purpose skills. However, acquiring inherent primitive skills in a coupled and long-horizon environment without external rewards or human supervision presents significant challenges. In this paper, we evaluate the relationship between skills and language instructions from a mathematical perspective, employing two forms of mutual information within the framework of language-conditioned policy learning. To maximize the mutual information between language and skills in an unsupervised manner, we propose an end-to-end imitation learning approach known as Language Conditioned Skill Discovery (LCSD). Specifically, we utilize vector quantization to learn discrete latent skills and leverage skill sequences of trajectories to reconstruct high-level semantic instructions. Through extensive experiments on language-conditioned robotic navigation and manipulation tasks, encompassing BabyAI, LORel, and CALVIN, we demonstrate the superiority of our method over prior works. Our approach exhibits enhanced generalization capabilities towards unseen tasks, improved skill interpretability, and notably higher rates of task completion success.

cs.RO↗

arXiv2024

Enhanced User Interaction in Operating Systems through Machine Learning Language Models

With the large language model showing human-like logical reasoning and understanding ability, whether agents based on the large language model can simulate the interaction behavior of real users, so as to build a reliable virtual recommendation A/B test scene to help the application of recommendation research is an urgent, important and economic value problem. The combination of interaction design and machine learning can provide a more efficient and personalized user experience for products and services. This personalized service can meet the specific needs of users and improve user satisfaction and loyalty. Second, the interactive system can understand the user's views and needs for the product by providing a good user interface and interactive experience, and then use machine learning algorithms to improve and optimize the product. This iterative optimization process can continuously improve the quality and performance of the product to meet the changing needs of users. At the same time, designers need to consider how these algorithms and tools can be combined with interactive systems to provide a good user experience. This paper explores the potential applications of large language models, machine learning and interaction design for user interaction in recommendation systems and operating systems. By integrating these technologies, more intelligent and personalized services can be provided to meet user needs and promote continuous improvement and optimization of products. This is of great value for both recommendation research and user experience applications.

cs.IR↗

arXiv2024

Enhancing Cloud-Based Large Language Model Processing with Elasticsearch and Transformer Models

Large Language Models (LLMs) are a class of generative AI models built using the Transformer network, capable of leveraging vast datasets to identify, summarize, translate, predict, and generate language. LLMs promise to revolutionize society, yet training these foundational models poses immense challenges. Semantic vector search within large language models is a potent technique that can significantly enhance search result accuracy and relevance. Unlike traditional keyword-based search methods, semantic search utilizes the meaning and context of words to grasp the intent behind queries and deliver more precise outcomes. Elasticsearch emerges as one of the most popular tools for implementing semantic search an exceptionally scalable and robust search engine designed for indexing and searching extensive datasets. In this article, we delve into the fundamentals of semantic search and explore how to harness Elasticsearch and Transformer models to bolster large language model processing paradigms. We gain a comprehensive understanding of semantic search principles and acquire practical skills for implementing semantic search in real-world model application scenarios.

cs.IR↗

arXiv2024

Data Pipeline Training: Integrating AutoML to Optimize the Data Flow of Machine Learning Models

Data Pipeline plays an indispensable role in tasks such as modeling machine learning and developing data products. With the increasing diversification and complexity of Data sources, as well as the rapid growth of data volumes, building an efficient Data Pipeline has become crucial for improving work efficiency and solving complex problems. This paper focuses on exploring how to optimize data flow through automated machine learning methods by integrating AutoML with Data Pipeline. We will discuss how to leverage AutoML technology to enhance the intelligence of Data Pipeline, thereby achieving better results in machine learning tasks. By delving into the automation and optimization of Data flows, we uncover key strategies for constructing efficient data pipelines that can adapt to the ever-changing data landscape. This not only accelerates the modeling process but also provides innovative solutions to complex problems, enabling more significant outcomes in increasingly intricate data domains. Keywords- Data Pipeline Training;AutoML; Data environment; Machine learning

cs.LG↗

arXiv2023

Password-Stealing without Hacking: Wi-Fi Enabled Practical Keystroke Eavesdropping

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches, yet existing attacks relying on Wi-Fi CSI (channel state information) demand hacking Wi-Fi hardware to obtain desired CSIs. Since such hacking has proven prohibitively hard due to compact hardware, its feasibility in keeping up with fast-developing Wi-Fi technology becomes very questionable. To this end, we propose WiKI-Eve to eavesdrop keystrokes on smartphones without the need for hacking. WiKI-Eve exploits a new feature, BFI (beamforming feedback information), offered by latest Wi-Fi hardware: since BFI is transmitted from a smartphone to an AP in clear-text, it can be overheard (hence eavesdropped) by any other Wi-Fi devices switching to monitor mode. As existing keystroke inference methods offer very limited generalizability, WiKI-Eve further innovates in an adversarial learning scheme to enable its inference generalizable towards unseen scenarios. We implement WiKI-Eve and conduct extensive evaluation on it; the results demonstrate that WiKI-Eve achieves 88.9% inference accuracy for individual keystrokes and up to 65.8% top-10 accuracy for stealing passwords of mobile applications (e.g., WeChat).

cs.CR↗

arXiv2023

MUSE-Fi: Contactless MUti-person SEnsing Exploiting Near-field Wi-Fi Channel Variation

Having been studied for more than a decade, Wi-Fi human sensing still faces a major challenge in the presence of multiple persons, simply because the limited bandwidth of Wi-Fi fails to provide a sufficient range resolution to physically separate multiple subjects. Existing solutions mostly avoid this challenge by switching to radars with GHz bandwidth, at the cost of cumbersome deployments. Therefore, could Wi-Fi human sensing handle multiple subjects remains an open question. This paper presents MUSE-Fi, the first Wi-Fi multi-person sensing system with physical separability. The principle behind MUSE-Fi is that, given a Wi-Fi device (e.g., smartphone) very close to a subject, the near-field channel variation caused by the subject significantly overwhelms variations caused by other distant subjects. Consequently, focusing on the channel state information (CSI) carried by the traffic in and out of this device naturally allows for physically separating multiple subjects. Based on this principle, we propose three sensing strategies for MUSE-Fi: i) uplink CSI, ii) downlink CSI, and iii) downlink beamforming feedback, where we specifically tackle signal recovery from sparse (per-user) traffic under realistic multi-user communication scenarios. Our extensive evaluations clearly demonstrate that MUSE-Fi is able to successfully handle multi-person sensing with respect to three typical applications: respiration monitoring, gesture detection, and activity recognition.

cs.NI↗

arXiv2023

Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering

Recent advances in Transformer architectures [1] have brought remarkable improvements to visual question answering (VQA). Nevertheless, Transformer-based VQA models are usually deep and wide to guarantee good performance, so they can only run on powerful GPU servers and cannot run on capacity-restricted platforms such as mobile phones. Therefore, it is desirable to learn an elastic VQA model that supports adaptive pruning at runtime to meet the efficiency constraints of different platforms. To this end, we present the bilaterally slimmable Transformer (BST), a general framework that can be seamlessly integrated into arbitrary Transformer-based VQA models to train a single model once and obtain various slimmed submodels of different widths and depths. To verify the effectiveness and generality of this method, we integrate the proposed BST framework with three typical Transformer-based VQA approaches, namely MCAN [2], UNITER [3], and CLIP-ViL [4], and conduct extensive experiments on two commonly-used benchmark datasets. In particular, one slimmed MCAN-BST submodel achieves comparable accuracy on VQA-v2, while being 0.38x smaller in model size and having 0.27x fewer FLOPs than the reference MCAN model. The smallest MCAN-BST submodel only has 9M parameters and 0.16G FLOPs during inference, making it possible to deploy it on a mobile device with less than 60 ms latency.

cs.CV↗

arXiv2023

AutoFed: Heterogeneity-Aware Federated Multimodal Learning for Robust Autonomous Driving

Object detection with on-board sensors (e.g., lidar, radar, and camera) play a crucial role in autonomous driving (AD), and these sensors complement each other in modalities. While crowdsensing may potentially exploit these sensors (of huge quantity) to derive more comprehensive knowledge, \textit{federated learning} (FL) appears to be the necessary tool to reach this potential: it enables autonomous vehicles (AVs) to train machine learning models without explicitly sharing raw sensory data. However, the multimodal sensors introduce various data heterogeneity across distributed AVs (e.g., label quantity skews and varied modalities), posing critical challenges to effective FL. To this end, we present AutoFed as a heterogeneity-aware FL framework to fully exploit multimodal sensory data on AVs and thus enable robust AD. Specifically, we first propose a novel model leveraging pseudo-labeling to avoid mistakenly treating unlabeled objects as the background. We also propose an autoencoder-based data imputation method to fill missing data modality (of certain AVs) with the available ones. To further reconcile the heterogeneity, we finally present a client selection mechanism exploiting the similarities among client models to improve both training stability and convergence rate. Our experiments on benchmark dataset confirm that AutoFed substantially improves over status quo approaches in both precision and recall, while demonstrating strong robustness to adverse weather conditions.

cs.LG↗

arXiv2023

DocRED-FE: A Document-Level Fine-Grained Entity And Relation Extraction Dataset

Joint entity and relation extraction (JERE) is one of the most important tasks in information extraction. However, most existing works focus on sentence-level coarse-grained JERE, which have limitations in real-world scenarios. In this paper, we construct a large-scale document-level fine-grained JERE dataset DocRED-FE, which improves DocRED with Fine-Grained Entity Type. Specifically, we redesign a hierarchical entity type schema including 11 coarse-grained types and 119 fine-grained types, and then re-annotate DocRED manually according to this schema. Through comprehensive experiments we find that: (1) DocRED-FE is challenging to existing JERE models; (2) Our fine-grained entity types promote relation classification. We make DocRED-FE with instruction and the code for our baselines publicly available at https://github.com/PKU-TANGENT/DOCRED-FE.

cs.CL↗

arXiv2022

Dynamic Interactional And Cooperative Network For Shield Machine

The shield machine (SM) is a complex mechanical device used for tunneling. However, the monitoring and deciding were mainly done by artificial experience during traditional construction, which brought some limitations, such as hidden mechanical failures, human operator error, and sensor anomalies. To deal with these challenges, many scholars have studied SM intelligent methods. Most of these methods only take SM into account but do not consider the SM operating environment. So, this paper discussed the relationship among SM, geological information, and control terminals. Then, according to the relationship, models were established for the control terminal, including SM rate prediction and SM anomaly detection. The experimental results show that compared with baseline models, the proposed models in this paper perform better. In the proposed model, the R2 and MSE of rate prediction can reach 92.2\%, and 0.0064 respectively. The abnormal detection rate of anomaly detection is up to 98.2\%.

cs.LG↗

arXiv2022

Synthesis and Superconductivity in yttrium superhydrides under high pressure

The flourishing rare earth superhydrides are a class of recently discovered materials that possess near-room-temperature superconductivity at high pressures, opening a new era of superconductivity research at high pressures. Among these superhydrides, yttrium superhydrides attracted great interest owing to their abundance of stoichiometries and excellent superconductivities. Here, we carried out a comprehensive study of yttrium superhydrides in a wide pressure range of 145-300 GPa. We successfully synthesized a series of superhydrides with the compositions of YH4, YH6, YH7, and YH9, and reported their superconducting transition temperatures of 82 K at 167 GPa, 218 K at 165 GPa, 29 K at 162 GPa, and 230 K at 300 GPa, respectively, which were evidenced by a sharp drop of resistivity. The structure and superconductivity of YH4, which was taken as a representative example, were also examined by X-ray diffraction measurements and the suppression of the superconductivity under external magnetic fields, respectively. Clathrate YH10 as a candidate of room-temperature superconductor was not synthesized within the studied pressure and temperature ranges of up to 300 GPa and 2000 K, respectively. The current work created a detailed platform for further searching room-temperature superconductors in polynary yttrium-based superhydrides.

cond-mat.supr-con↗

arXiv2022

Efficient route to achieve superconductivity improvement via substitutional La-Ce alloy superhydride at high pressure

The discovery of clathrate superhydrides has approached the long-standing dream of room-temperature superconductivity and thus inspired their prosperous research under high pressure. However, how to experimentally optimize these compelling superhydrides is still a formidable challenge. Here, we find that half of the Ce atoms in the recently discovered hexagonal close packed (hcp) CeH9 structure can be randomly replaced by adjacent La, resulting in the formation of LaH9 unit that is impossible in a binary system. Our experiments show that hcp (La, Ce)H9 can be synthesized at ~110 GPa and possesses a maximum Tc of 178 K at higher pressure, which is evidenced by in-situ X-ray diffraction and electronic transport measurement where a sharp drop of resistivity to zero and a characteristic decrease of Tc under a magnetic field up to 9 T. More importantly, the Tc of (La, Ce)H9 is significantly increased by ~50-80 K compared to CeH9, showing the hitherto highest Tc at megabar pressure. Our experimental results not only verify the feasibility of improving the superconductivity of hydrides by introducing other suitable metals, but also provide important inspiration for finding high-Tc superconductors in various multinary superhydrides.

cond-mat.supr-con↗

arXiv2021

High-Tc superconductivity in clathrate calcium hydride CaH6

Recent discovery of superconductive rare earth/actinide superhydrides has ushered in a new era of superconductivity research at high pressures. This distinct type of clathrate metal hydrides was first proposed for alkaline-earth-metal hydride CaH6 that, however, has long eluded experimental synthesis, impeding an understanding of pertinent physics. Here, we report successful synthesis of CaH6 and its measured superconducting critical temperature Tc of 215 K at 172 GPa, which is evidenced by a sharp drop of resistivity to zero and a characteristic decrease of Tc under a magnetic field up to 9 T.An estimate based on the Werthamer-Helfand-Hohenberg model gives a giant zero-temperature upper critical magnetic field of 203 T. These remarkable benchmark superconducting properties place CaH6 among the most outstanding high-Tc superhydrides, marking it as the hitherto only clathrate metal hydride outside the family of rare earth/actinide hydrides. This exceptional case raises great prospects of expanding the extraordinary class of high-Tc superhydrides to a broader variety of compounds that possess more diverse material features and physics characteristics.

cond-mat.supr-con↗