JZJun Zhuang

Jun Zhuang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Jun Zhuang has a total of 54 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Hierarchical Memory for Radiology Report Generation with Rich Context

    by Qingyue Jiao, Jiahao Zheng, Jun Zhuang, Yiyu Shi

  • Open Access

    Benchmarking Barren Plateau Mitigation Strategies in Quantum Neural Networks on Standard and Medical Image Datasets

    by Maqsudur Rahman, Rui Liu, Anup Majumder, Pintu Chandra Paul, Kangtong Mo, Amena Begum, Kashmi Sultana, Nahida Akter, Lu Wei, Ye Zhang, et al.

    Barren plateaus (BPs) pose a major trainability challenge for quantum neural networks (QNNs) by causing gradients to concentrate near zero as circuit size, depth, or expressibility increases. This study presents a comparative benchmark of 10 BP mitigation strategies across six qubit settings (2, 4, 8, 12, 16, and 20) and three datasets of increasing complexity: Iris, MNIST, and MedMNIST. The evaluated methods include eight initialization-based strategies (Beta, Gaussian, Uniform Norm, CNN-based initialization, He-normal, He-uniform, Xavier-normal, and Xavier-uniform), one model-based variational encoder, and one optimization-based time-nonlocal Fourier parameterization. Experiments were implemented using PennyLane 3.10 and PyTorch 2.5 with simulator backends. We evaluate trainability using gradient variance and training loss, and we clarify that the benchmark analyzes simulated QNN optimization behavior rather than hardware-noise-resilient or noisy-label learning. Across the tested two-layer circuit configurations, the mitigation strategies maintained measurable gradient variance and stable loss reduction, suggesting that severe barren plateau behavior was not observed under the benchmark conditions. CNN-based and Beta initialization showed strong empirical behavior in variance retention and convergence speed, while Gaussian initialization was comparatively weaker in higher-dimensional settings. The study provides a reproducible benchmark structure for comparing BP mitigation behavior and identifies important limitations related to circuit depth, hardware noise, feature encoding, and classification performance that should be addressed in future QNN benchmarking.

  • Open Access

    Systems-Level Support for Hybrid Quantum-Classical Learning: A Systematic Review with a Medical Imaging Translation Lens

    by Maqsudur Rahman, Pintu Chandra Paul, Amena Begum, Kashmi Sultana, Nahida Akter, Anup Majumder, Mengran Zhu, Ze Sheng, Wangjiaxuan Xin, Xin Jin, et al.

    Hybrid quantum-classical learning pipelines combine conventional accelerators, quantum runtimes, and quantum processing units (QPUs), creating scheduling, memory, isolation, encoding, and deployment challenges that are not captured by application-level quantum machine learning surveys alone. This paper presents a systematic review of runtime and systems mechanisms for hybrid quantum-classical workloads, with medical imaging used as a translation lens rather than as an exclusive inclusion boundary. Following a PRISMA-aligned review process, we screened 364 records and synthesized 40 studies published between 2020 and 2025. Each study was coded by systems layer, application grounding, noisy-label relevance, and evaluation maturity. The coding shows that the corpus combines direct medical evidence with broader transferable systems evidence: 8 studies directly evaluated medical data, 12 were medically motivated, and 20 were generic systems studies. Across the corpus, the strongest support concerns hybrid orchestration, qubit/resource allocation, classical–quantum data movement, and container-based reproducibility, whereas evidence remains limited for realistic clinical operation, end-to-end remote-QPU workflows, multi-tenant isolation, and noisy-label retraining loops. We contribute an evidence map, a direct/indirect/interpretive evidence distinction, and cross-layer design guidelines for future hybrid quantum-classical imaging pipelines in regulated settings.

  • Open Access

    Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models

    by Ye Yu, Haibo Jin, Yaoning Yu, Jun Zhuang, Haohan Wang

    Large audio-language models increasingly operate on raw speech inputs, enabling more seamless integration across domains such as voice assistants, education, and clinical triage. This transition, however, introduces a distinct class of vulnerabilities that remain largely uncharacterized. We examine the security implications of this modality shift by designing a text-to-audio jailbreak that embeds disallowed directives within a narrative-style audio stream. The attack leverages an advanced instruction-following text-to-speech (TTS) model to exploit structural and acoustic properties, thereby circumventing safety mechanisms primarily calibrated for text. When delivered through synthetic speech, the narrative format elicits restricted outputs from state-of-the-art models, including Gemini 2.0 Flash, achieving a 98.26% success rate that substantially exceeds text-only baselines. These results highlight the need for safety frameworks that jointly reason over linguistic and paralinguistic representations, particularly as speech-based interfaces become more prevalent.

  • Top Cited Papers
    Open Access

    Deconstructing the ethics of large language models from long-standing issues to new-emerging dilemmas: a survey

    by Chengyuan Deng, Yiqun Duan, Xin Jin, Heng Chang, Yijun Tian, Han Liu, Yichen Wang, Kuofeng Gao, Henry Peng Zou, Yiqiao Jin, et al.

    Large Language Models (LLMs) have achieved unparalleled success across diverse language modeling tasks in recent years. However, this progress has also intensified ethical concerns, impacting the deployment of LLMs in everyday contexts. This paper provides a comprehensive survey of ethical challenges associated with LLMs, from longstanding issues such as copyright infringement, systematic bias, and data privacy, to emerging problems like truthfulness and social norms. We critically analyze existing research aimed at understanding, examining, and mitigating these ethical risks. Our survey underscores integrating ethical standards and societal values into the development of LLMs, thereby guiding the development of responsible and ethically aligned language models.


  • Open Access

    InfoFlood: Jailbreaking Large Language Models with Information Overload

    by Advait Yadav, Haibo Jin, Man Luo, Jun Zhuang, Haohan Wang

    Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing jailbreak methods typically involve appending carefully crafted prefixes or suffixes to malicious prompts in order to bypass the built-in safety mechanisms of these models. In this work, we identify a new vulnerability in which excessive linguistic complexity can disrupt built-in safety mechanisms-without the need for any added prefixes or suffixes-allowing attackers to elicit harmful outputs directly. We refer to this phenomenon as Information Overload. To automatically exploit this vulnerability, we propose InfoFlood, a jailbreak attack that transforms malicious queries into complex, information-overloaded queries capable of bypassing built-in safety mechanisms. Specifically, InfoFlood: (1) uses linguistic transformations to rephrase malicious queries, (2) identifies the root cause of failure when an attempt is unsuccessful, and (3) refines the prompt's linguistic structure to address the failure while preserving its malicious intent. We empirically validate the effectiveness of InfoFlood on four widely used LLMs-GPT-4o, GPT-3.5-turbo, Gemini 2.0, and LLaMA 3.1-by measuring their jailbreak success rates. InfoFlood consistently outperforms baseline attacks, achieving up to 3 times higher success rates across multiple jailbreak benchmarks. Furthermore, we demonstrate that commonly adopted post-processing defenses, including OpenAI's Moderation API, Perspective API, and SmoothLLM, fail to mitigate these attacks. This highlights a critical weakness in traditional AI safety guardrails when confronted with information overload-based jailbreaks.


  • Top Cited Papers
    Open Access

    Investigating and mitigating barren plateaus in variational quantum circuits: a survey

    by Jack Cunningham, Jun Zhuang

    In recent years, variational quantum circuits (VQCs) have been widely explored to advance quantum circuits against classic models on various domains, such as quantum chemistry and quantum machine learning. Similar to classic machine-learning models, VQCs can be trained through various optimization approaches, such as gradient-based or gradient-free methods. However, when employing gradient-based methods, the gradient variance of VQCs may dramatically vanish as the number of qubits or layers increases. This issue, a.k.a. barren plateaus (BPs), seriously hinders the scaling of VQCs on large datasets. To mitigate the barren plateaus, extensive efforts have been devoted to tackling this issue through diverse strategies. In this survey, we conduct a systematic literature review of recent works from both investigation and mitigation perspectives. Furthermore, we propose a new taxonomy to categorize most existing mitigation strategies into five groups and introduce them in detail. Also, we compare the concurrent survey papers about BPs. Finally, we provide insightful discussion on future directions for BPs.


  • Open Access

    Investigating Parameter Initialization Techniques in Variational Quantum Circuits

    by Jack Cunningham, Jun Zhuang

    Variational Quantum Circuits (VQC)s have been widely explored to advance quantum circuits against classic models in various domains. Similar to classic machine-learning models, VQCs can be optimized through gradient-based approaches. However, the gradient of VQCs may dramatically vanish during the optimization process for various reasons. This issue, known as Barren Plateaus (BP)s, seriously hinders the advancement of quantum computing. To mitigate BPs, extensive efforts have been devoted to tackling this issue through different methods. In this work, we aim to investigate several circuit components through the lens of parameter initialization techniques. We study the performance and gradient variance of the different quantum circuit structures in combination with various initialization methods. This investigation will provide a better understanding of how the VQC structures behave under different initialization strategies for binary classification problems.

  • Open Access

    Trustworthy and Responsible AI for Information and Knowledge Management System

    by Huaming Chen, Jun Zhuang, Yu Yao, Wei Jin, Haohan Wang, Yong Xie, Chi-Hung Chi, Kim-Kwang Raymond Choo

    The way research and business manage and utilize knowledge is undergoing a significant transformation, driven by Artificial Intelligence (AI). Deep learning and machine learning are emerging as powerful tools for optimizing knowledge management systems, leading to more informed and productive development. AI offers unique solutions for organizations struggling with information overload and inefficient knowledge transfer. These AI models can significantly improve data management and utilization. Imagine an AI-powered system that streamlines onboarding processes, provides precise answers to various queries, and even captures the valuable tacit knowledge (implicit skills and expertise) often residing within individuals. AI bridges the gap between explicit knowledge (easily documented information) and tacit knowledge, fostering a more comprehensive and accessible knowledge base. However, such AI systems solicit trustworthy and responsible approaches to mitigate potential misuse and malfunction. In this workshop, we aim to gather researchers and engineers from academia and industry to discuss the latest advances in trustworthy and responsible AI solutions for information and knowledge management systems.