arXiv subjects

Yixuan Zhang

Publications and source records attributed to Yixuan Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Understanding the Practices, Perceptions, and (Dis)Trust of Generative AI among Instructors: A Mixed-methods Study in the U.S. Higher Education

Generative AI (GenAI) has brought opportunities and challenges for higher education as it integrates into teaching and learning environments. As instructors navigate this new landscape, understanding their engagement with and attitudes toward GenAI is crucial. We surveyed 178 instructors from a single U.S. university to examine their current practices, perceptions, trust, and distrust of GenAI in higher education in March 2024. While most surveyed instructors reported moderate to high familiarity with GenAI-related concepts, their actual use of GenAI tools for direct instructional tasks remained limited. Our quantitative results show that trust and distrust in GenAI are related yet distinct; high trust does not necessarily imply low distrust, and vice versa. We also found significant differences in surveyed instructors' familiarity with GenAI across different trust and distrust groups. Our qualitative results show nuanced manifestations of trust and distrust among surveyed instructors and various approaches to support calibrated trust in GenAI. We discuss practical implications focused on (dis)trust calibration among instructors.

cs.HC↗

arXiv2025

A computational loudness model for electrical stimulation with cochlear implants

Cochlear implants (CIs) are devices that restore the sense of hearing in people with severe sensorineural hearing loss. An electrode array inserted in the cochlea bypasses the natural transducer mechanism that transforms mechanical sound waves into neural activity by artificially stimulating the auditory nerve fibers with electrical pulses. The perception of sounds is possible because the brain extracts features from this neural activity, and loudness is among the most fundamental perceptual features. A computational model that uses a three-dimensional (3D) representation of the peripheral auditory system of CI users was developed to predict categorical loudness from the simulated peripheral neural activity. In contrast, current state-of-the-art computational loudness models predict loudness from the electrical pulses with minimal parametrization of the electrode-nerve interface. In the proposed model, the spikes produced in a population of auditory nerve fibers were grouped by cochlear places, a physiological representation of the auditory filters in psychoacoustics, to be transformed into loudness contribution. Then, a loudness index was obtained with a spatiotemporal integration over this loudness contribution. This index served to define the simulated threshold of hearing (THL) and most comfortable loudness (MCL) levels resembling the growth function in CI users. The performance of real CI users in loudness summation experiments was also used to validate the computational model. These experiments studied the effect of stimulation rate, electrode separation and amplitude modulation. The proposed model provides a new set of perceptual features that can be used in computational frameworks for CIs and narrows the gap between simulations and the human peripheral neural activity.

q-bio.NC↗

arXiv2025

Evaluating an LLM-Powered Chatbot for Cognitive Restructuring: Insights from Mental Health Professionals

Recent advancements in large language models (LLMs) promise to expand mental health interventions by emulating therapeutic techniques, potentially easing barriers to care. Yet there is a lack of real-world empirical evidence evaluating the strengths and limitations of LLM-enabled psychotherapy interventions. In this work, we evaluate an LLM-powered chatbot, designed via prompt engineering to deliver cognitive restructuring (CR), with 19 users. Mental health professionals then examined the resulting conversation logs to uncover potential benefits and pitfalls. Our findings indicate that an LLM-based CR approach has the capability to adhere to core CR protocols, prompt Socratic questioning, and provide empathetic validation. However, issues of power imbalances, advice-giving, misunderstood cues, and excessive positivity reveal deeper challenges, including the potential to erode therapeutic rapport and ethical concerns. We also discuss design implications for leveraging LLMs in psychotherapy and underscore the importance of expert oversight to mitigate these concerns, which are critical steps toward safer, more effective AI-assisted interventions.

cs.HC↗

arXiv2025

Understanding Attitudes and Trust of Generative AI Chatbots for Social Anxiety Support

Social anxiety (SA) has become increasingly prevalent. Traditional coping strategies often face accessibility challenges. Generative AI (GenAI), known for their knowledgeable and conversational capabilities, are emerging as alternative tools for mental well-being. With the increased integration of GenAI, it is important to examine individuals' attitudes and trust in GenAI chatbots' support for SA. Through a mixed-method approach that involved surveys (n = 159) and interviews (n = 17), we found that individuals with severe symptoms tended to trust and embrace GenAI chatbots more readily, valuing their non-judgmental support and perceived emotional comprehension. However, those with milder symptoms prioritized technical reliability. We identified factors influencing trust, such as GenAI chatbots' ability to generate empathetic responses and its context-sensitive limitations, which were particularly important among individuals with SA. We also discuss the design implications and use of GenAI chatbots in fostering cognitive and emotional trust, with practical and design considerations.

cs.HC↗

arXiv2024

SuperSalt: Equivariant Neural Network Force Fields for Multicomponent Molten Salts System

Molten salts are crucial for clean energy applications, yet exploring their thermophysical properties across diverse chemical space remains challenging. We present the development of a machine learning interatomic potential (MLIP) called SuperSalt, which targets 11-cation chloride melts and captures the essential physics of molten salts with near-DFT accuracy. Using an efficient workflow that integrates systems of one, two, and 11 components, the SuperSalt potential can accurately predict thermophysical properties such as density, bulk modulus, thermal expansion, and heat capacity. Our model is validated across a broad chemical space, demonstrating excellent transferability. We further illustrate how Bayesian optimization combined with SuperSalt can accelerate the discovery of optimal salt compositions with desired properties. This work provides a foundation for future studies that allows easy extensions to more complex systems, such as those containing additional elements. SuperSalt represents a shift towards a more universal, efficient, and accurate modeling of molten salts for advanced energy applications.

cond-mat.mtrl-sci↗

arXiv2024

Task Diversity in Bayesian Federated Learning: Simultaneous Processing of Classification and Regression

This work addresses a key limitation in current federated learning approaches, which predominantly focus on homogeneous tasks, neglecting the task diversity on local devices. We propose a principled integration of multi-task learning using multi-output Gaussian processes (MOGP) at the local level and federated learning at the global level. MOGP handles correlated classification and regression tasks, offering a Bayesian non-parametric approach that naturally quantifies uncertainty. The central server aggregates the posteriors from local devices, updating a global MOGP prior redistributed for training local models until convergence. Challenges in performing posterior inference on local devices are addressed through the Pólya-Gamma augmentation technique and mean-field variational inference, enhancing computational efficiency and convergence rate. Experimental results on both synthetic and real data demonstrate superior predictive performance, OOD detection, uncertainty calibration and convergence rate, highlighting the method's potential in diverse applications. Our code is publicly available at https://github.com/JunliangLv/task_diversity_BFL.

cs.LG↗

arXiv2024

Hierarchical Multi-Graphs Learning for Robust Group Re-Identification

Group Re-identification (G-ReID) faces greater complexity than individual Re-identification (ReID) due to challenges like mutual occlusion, dynamic member interactions, and evolving group structures. Prior graph-based approaches have aimed to capture these dynamics by modeling the group as a single topological structure. However, these methods struggle to generalize across diverse group compositions, as they fail to fully represent the multifaceted relationships within the group. In this study, we introduce a Hierarchical Multi-Graphs Learning (HMGL) framework to address these challenges. Our approach models the group as a collection of multi-relational graphs, leveraging both explicit features (such as occlusion, appearance, and foreground information) and implicit dependencies between members. This hierarchical representation, encoded via a Multi-Graphs Neural Network (MGNN), allows us to resolve ambiguities in member relationships, particularly in complex, densely populated scenes. To further enhance matching accuracy, we propose a Multi-Scale Matching (MSM) algorithm, which mitigates issues of member information ambiguity and sensitivity to hard samples, improving robustness in challenging scenarios. Our method achieves state-of-the-art performance on two standard benchmarks, CSG and RoadGroup, with Rank-1/mAP scores of 95.3%/94.4% and 93.9%/95.4%, respectively. These results mark notable improvements of 1.7% and 2.5% in Rank-1 accuracy over existing approaches.

cs.CV↗

arXiv2024

Nonstationary Sparse Spectral Permanental Process

Existing permanental processes often impose constraints on kernel types or stationarity, limiting the model's expressiveness. To overcome these limitations, we propose a novel approach utilizing the sparse spectral representation of nonstationary kernels. This technique relaxes the constraints on kernel types and stationarity, allowing for more flexible modeling while reducing computational complexity to the linear level. Additionally, we introduce a deep kernel variant by hierarchically stacking multiple spectral feature mappings, further enhancing the model's expressiveness to capture complex patterns in data. Experimental results on both synthetic and real-world datasets demonstrate the effectiveness of our approach, particularly in scenarios with pronounced data nonstationarity. Additionally, ablation studies are conducted to provide insights into the impact of various hyperparameters on model performance.

stat.ML↗

arXiv2024

Navigating Towards Fairness with Data Selection

Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness. Existing fairness techniques that address label bias typically involve modifying models and intervening in the training process, but these lack flexibility for large-scale datasets. To address this limitation, we introduce a data selection method designed to efficiently and flexibly mitigate label bias, tailored to more practical needs. Our approach utilizes a zero-shot predictor as a proxy model that simulates training on a clean holdout set. This strategy, supported by peer predictions, ensures the fairness of the proxy model and eliminates the need for an additional holdout set, which is a common requirement in previous methods. Without altering the classifier's architecture, our modality-agnostic method effectively selects appropriate training data and has proven efficient and effective in handling label bias and improving fairness across diverse datasets in experimental evaluations.

cs.LG↗

arXiv2024

Automatic State Machine Inference for Binary Protocol Reverse Engineering

Protocol Reverse Engineering (PRE) is used to analyze protocols by inferring their structure and behavior. However, current PRE methods mainly focus on field identification within a single protocol and neglect Protocol State Machine (PSM) analysis in mixed protocol environments. This results in insufficient analysis of protocols' abnormal behavior and potential vulnerabilities, which are crucial for detecting and defending against new attack patterns. To address these challenges, we propose an automatic PSM inference framework for unknown protocols, including a fuzzy membership-based auto-converging DBSCAN algorithm for protocol format clustering, followed by a session clustering algorithm based on Needleman-Wunsch and K-Medoids algorithms to classify sessions by protocol type. Finally, we refine a probabilistic PSM algorithm to infer protocol states and the transition conditions between these states. Experimental results show that, compared with existing PRE techniques, our method can infer PSMs while enabling more precise classification of protocols.

cs.CR↗

arXiv2024

OOD-HOI: Text-Driven 3D Whole-Body Human-Object Interactions Generation Beyond Training Domains

Generating realistic 3D human-object interactions (HOIs) from text descriptions is a active research topic with potential applications in virtual and augmented reality, robotics, and animation. However, creating high-quality 3D HOIs remains challenging due to the lack of large-scale interaction data and the difficulty of ensuring physical plausibility, especially in out-of-domain (OOD) scenarios. Current methods tend to focus either on the body or the hands, which limits their ability to produce cohesive and realistic interactions. In this paper, we propose OOD-HOI, a text-driven framework for generating whole-body human-object interactions that generalize well to new objects and actions. Our approach integrates a dual-branch reciprocal diffusion model to synthesize initial interaction poses, a contact-guided interaction refiner to improve physical accuracy based on predicted contact areas, and a dynamic adaptation mechanism which includes semantic adjustment and geometry deformation to improve robustness. Experimental results demonstrate that our OOD-HOI could generate more realistic and physically plausible 3D interaction pose in OOD scenarios compared to existing methods.

cs.CV↗

arXiv2024

Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

Generative models are rapidly gaining popularity and being integrated into everyday applications, raising concerns over their safe use as various vulnerabilities are exposed. In light of this, the field of red teaming is undergoing fast-paced growth, highlighting the need for a comprehensive survey covering the entire pipeline and addressing emerging topics. Our extensive survey, which examines over 120 papers, introduces a taxonomy of fine-grained attack strategies grounded in the inherent capabilities of language models. Additionally, we have developed the "searcher" framework to unify various automatic red teaming approaches. Moreover, our survey covers novel areas including multimodal attacks and defenses, risks around LLM-based agents, overkill of harmless queries, and the balance between harmlessness and helpfulness.

cs.CL↗

arXiv2024

IC Mechanisms for Risk-Averse Advertisers in the Online Advertising System

The autobidding system generates huge revenue for advertising platforms, garnering substantial research attention. Existing studies in autobidding systems focus on designing Autobidding Incentive Compatible (AIC) mechanisms, where the mechanism is Incentive Compatible (IC) under ex ante expectations. However, upon deploying AIC mechanisms in advertising platforms, we observe a notable deviation between the actual auction outcomes and these expectations during runtime, particularly in the scene with few clicks (sparse-click). This discrepancy undermines truthful bidding among advertisers in AIC mechanisms, especially for risk-averse advertisers who are averse to outcomes that do not align with the expectations. To address this issue, we propose a mechanism, Decoupled First-Price Auction (DFP), that retains its IC property even during runtime. DFP dynamically adjusts the payment based on real-time user conversion outcomes, ensuring that advertisers' realized utilities closely approximate their expected utilities during runtime. To realize the payment mechanism of DFP, we propose a PPO-based RL algorithm, with a meticulously crafted reward function. This algorithm dynamically adjusts the payment to fit DFP mechanism. We conduct extensive experiments leveraging real-world data to validate our findings.

cs.GT↗

arXiv2024

Research on WebAssembly Runtimes: A Survey

WebAssembly (abbreviated as Wasm) was initially introduced for the Web but quickly extended its reach into various domains beyond the Web. To create Wasm applications, developers can compile high-level programming languages into Wasm binaries or manually convert equivalent textual formats into Wasm binaries. Regardless of whether it is utilized within or outside the Web, the execution of Wasm binaries is supported by the Wasm runtime. Such a runtime provides a secure, memory-efficient, and sandboxed execution environment designed explicitly for Wasm applications. This paper provides a comprehensive survey of research on WebAssembly runtimes. It covers 98 articles on WebAssembly runtimes and characterizes existing studies from two different angles, including the "internal" research of Wasm runtimes(Wasm runtime design, testing, and analysis) and the "external" research(applying Wasm runtimes to various domains). This paper also proposes future research directions about WebAssembly runtimes.

cs.SE↗

arXiv2024

TrustLLM: Trustworthiness in Large Language Models

Large language models (LLMs), exemplified by ChatGPT, have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. Therefore, ensuring the trustworthiness of LLMs emerges as an important topic. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and utility (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Finally, we emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. Knowing the specific trustworthy technologies that have been employed is crucial for analyzing their effectiveness.

cs.CL↗

arXiv2024

Generative deep learning for the inverse design of materials

In addition to the forward inference of materials properties using machine learning, generative deep learning techniques applied on materials science allow the inverse design of materials, i.e., assessing the composition-processing-(micro-)structure-property relationships in a reversed way. In this review, we focus on the (micro-)structure-property mapping, i.e., crystal structure-intrinsic property and microstructure-extrinsic property, and summarize comprehensively how generative deep learning can be performed. Three key elements, i.e., the construction of latent spaces for both the crystal structures and microstructures, generative learning approaches, and property constraints, are discussed in detail. A perspective is given outlining the challenges of the existing methods in terms of computational resource consumption, data compatibility, and yield of generation.

cond-mat.mtrl-sci↗

arXiv2024

Stable diffusion for the inverse design of microstructures

In materials science, microstructures and their associated extrinsic properties are critical for engineering advanced structural and functional materials, yet their robust reconstruction and generation remain significant challenges. In this work, we developed a microstructure generation model based on the Stable Diffusion (SD) model, training it on a dataset of 576,000 2D synthetic microstructures containing both phase and grain orientation information. This model was applied to a range of tasks, including microstructure reconstruction, interpolation, inpainting, and generation. Experimental results demonstrate that our image-based approach can analyze and generate complex microstructural features with exceptional statistical and morphological fidelity. Additionally, by integrating the ControlNet fine-tuning model, we achieved the inverse design of microstructures based on specific properties. Compared to conventional methods, our approach offers greater accuracy, efficiency, and versatility, showcasing its generative potential in exploring previously uncharted microstructures and paving the way for data-driven development of advanced materials with tailored properties.

cond-mat.mtrl-sci↗

arXiv2024

Evaluating electrophysiological and behavioral measures of neural health in cochlear implant users: a computational simulation study

Neural health refers to the condition and functionality of the auditory nerve fibers (ANFs),which are crucial for transmitting sound signals from the cochlea to the brain.However, neural health cannot be directly measured due to current technological limitations. We utilize a computational model to evaluate different indirect methods for estimating ANF neural health.Two distinct measures for estimating neural health,(i)the threshold levels for focused quadrupolar stimulation and (ii) the change in the electrically evoked compound action potential (eCAP) amplitude growth function for different inter-phase gaps (IPGs), were evaluated in a computational model of an electrically stimulated implanted cochlea. The model combined a 3D finite element method model, an ANF geometry with a realistic spatial distribution, and a neuron model, including an existing phenomenological single-ANF model and an eCAP model. Our experiments simulated different neural health conditions (healthy, shrinked, and degenerated) to model dead regions in different locations of the cochlea.The results from the computational experiments demonstrated that the threshold levels with focused quadrupolar stimulation were more sensitive to neural health deficits than thresholds with monopolar stimulation. From our data, the difference in threshold levels between quadrupolar and monopolar stimulation seems to be a promising measure of neural health status. However, the results from the eCAP IPG slope and offset effects were not consistently associated with neural health conditions.Our results suggest that the difference in threshold levels with quadrupolar and monopolar stimulation is a possible method for estimating neural health. Significance: This study enhances the understanding of neural health and dead regions through a novel computational model, contributing to new approaches for neural health estimation.

physics.med-ph↗