arXiv subjects

Yifan Sun

Publications and source records attributed to Yifan Sun.

At least 109 records · Page 6Linked to original sources

arXiv2025

The Staircase of Ethics: Probing LLM Value Priorities through Multi-Step Induction to Complex Moral Dilemmas

Ethical decision-making is a critical aspect of human judgment, and the growing use of LLMs in decision-support systems necessitates a rigorous evaluation of their moral reasoning capabilities. However, existing assessments primarily rely on single-step evaluations, failing to capture how models adapt to evolving ethical challenges. Addressing this gap, we introduce the Multi-step Moral Dilemmas (MMDs), the first dataset specifically constructed to evaluate the evolving moral judgments of LLMs across 3,302 five-stage dilemmas. This framework enables a fine-grained, dynamic analysis of how LLMs adjust their moral reasoning across escalating dilemmas. Our evaluation of nine widely used LLMs reveals that their value preferences shift significantly as dilemmas progress, indicating that models recalibrate moral judgments based on scenario complexity. Furthermore, pairwise value comparisons demonstrate that while LLMs often prioritize the value of care, this value can sometimes be superseded by fairness in certain contexts, highlighting the dynamic and context-dependent nature of LLM ethical reasoning. Our findings call for a shift toward dynamic, context-aware evaluation paradigms, paving the way for more human-aligned and value-sensitive development of LLMs.

cs.CL↗

arXiv2025

Origin Identification for Text-Guided Image-to-Image Diffusion Models

Text-guided image-to-image diffusion models excel in translating images based on textual prompts, allowing for precise and creative visual modifications. However, such a powerful technique can be misused for spreading misinformation, infringing on copyrights, and evading content tracing. This motivates us to introduce the task of origin IDentification for text-guided Image-to-image Diffusion models (ID$^2$), aiming to retrieve the original image of a given translated query. A straightforward solution to ID$^2$ involves training a specialized deep embedding model to extract and compare features from both query and reference images. However, due to visual discrepancy across generations produced by different diffusion models, this similarity-based approach fails when training on images from one model and testing on those from another, limiting its effectiveness in real-world applications. To solve this challenge of the proposed ID$^2$ task, we contribute the first dataset and a theoretically guaranteed method, both emphasizing generalizability. The curated dataset, OriPID, contains abundant Origins and guided Prompts, which can be used to train and test potential IDentification models across various diffusion models. In the method section, we first prove the existence of a linear transformation that minimizes the distance between the pre-trained Variational Autoencoder (VAE) embeddings of generated samples and their origins. Subsequently, it is demonstrated that such a simple linear transformation can be generalized across different diffusion models. Experimental results show that the proposed method achieves satisfying generalization performance, significantly surpassing similarity-based methods ($+31.6\%$ mAP), even those with generalization designs. The project is available at https://id2icml.github.io.

cs.CV↗

arXiv2025

FullStack Bench: Evaluating LLMs as Full Stack Coders

As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing. However, most existing datasets only evaluate limited application domains. To address this gap, we have developed a comprehensive code evaluation dataset FullStack Bench focusing on full-stack programming, which encompasses a wide range of application domains (e.g., basic programming, data analysis, software engineering, mathematics, and machine learning). Besides, to assess multilingual programming capabilities, in FullStack Bench, we design real-world instructions and corresponding unit test cases from 16 widely-used programming languages to reflect real-world usage scenarios rather than simple translations. Moreover, we also release an effective code sandbox execution tool (i.e., SandboxFusion) supporting various programming languages and packages to evaluate the performance of our FullStack Bench efficiently. Comprehensive experimental results on our FullStack Bench demonstrate the necessity and effectiveness of our FullStack Bench and SandboxFusion.

cs.AI↗

arXiv2025

Will Your Next Pair Programming Partner Be Human? An Empirical Evaluation of Generative AI as a Collaborative Teammate in a Semester-Long Classroom Setting

Generative AI (GenAI), especially Large Language Models (LLMs), is rapidly reshaping both programming workflows and computer science education. Many programmers now incorporate GenAI tools into their workflows, including for collaborative coding tasks such as pair programming. While prior research has demonstrated the benefits of traditional pair programming and begun to explore GenAI-assisted coding, the role of LLM-based tools as collaborators in pair programming remains underexamined. In this work, we conducted a mixed-methods study with 39 undergraduate students to examine how GenAI influences collaboration, learning, and performance in pair programming. Specifically, students completed six in-class assignments under three conditions: Traditional Pair Programming (PP), Pair Programming with GenAI (PAI), and Solo Programming with GenAI (SAI). They used both LLM-based inline completion tools (e.g., GitHub Copilot) and LLM-based conversational tools (e.g., ChatGPT). Our results show that students in PAI achieved the highest assignment scores, whereas those in SAI attained the lowest. Additionally, students' attitudes toward LLMs' programming capabilities improved significantly after collaborating with LLM-based tools, and preferences were largely shaped by the perceived usefulness for completing assignments and learning programming skills, as well as the quality of collaboration. Our qualitative findings further reveal that while students appreciated LLM-based tools as valuable pair programming partners, they also identified limitations and had different expectations compared to human teammates. Our study provides one of the first empirical evaluations of GenAI as a pair programming collaborator through a comparison of three conditions (PP, PAI, and SAI). We also discuss the design implications and pedagogical considerations for future GenAI-assisted pair programming approaches.

cs.HC↗

arXiv2025

Distributed Reconstruction from Compressive Measurements: Nonconvexity and Heterogeneity

The compressive sensing (CS) and 1-bit CS demonstrate superior efficiency in signal acquisition and resource conservation, while 1-bit CS achieves maximum resource efficiency through sign-only measurements. With the emergence of massive data, the distributed signal aggregation under CS and 1-bit CS measurements introduces many challenges, including nonconvexity and heterogeneity. The nonconvexity originates from the unidentifiability of signal magnitude under finite-precision measurements. The heterogeneity arises from the signal and noisy measurement on each node. To address these challenges, we propose a framework with a squared cosine similarity penalty. We address nonconvexity by an novel invex relaxation formulation to ensure the uniqueness of the global optimality. For heterogeneous signals and noisy measurements, the proposed estimate adaptively debiases through correction guided by similarity and signal-to-noise ratio (SNR) information. Our method achieves a high probability minimax-optimal convergence rate under sufficient node counts and similarity conditions, improving from $O\{(p\log{p}/n_j)^{1/2}\}$ to $O\{(p\log{p}/N)^{1/2}+p^{1/2}/n_j\}$, with signal dimension $p$, local and total sizes $n_j$ and $N$. Extensive simulations validate the method's effectiveness and performance gains in reconstructing heterogeneous signals from 1-bit CS measurements. The proposed framework maintains applicability to CS measurements while reducing communication overhead in distributed setting.

stat.ME↗

arXiv2025

Advancing Multi-Secant Quasi-Newton Methods for General Convex Functions

Quasi-Newton (QN) methods provide an efficient alternative to second-order methods for minimizing smooth unconstrained problems. While QN methods generally compose a Hessian estimate based on one secant interpolation per iteration, multisecant methods use multiple secant interpolations and can improve the quality of the Hessian estimate at small additional overhead cost. However, implementing multisecant QN methods has several key challenges involving method stability, the most critical of which is that when the objective function is convex but not quadratic, the Hessian approximate is not, in general, symmetric positive semidefinite (PSD), and the steps are not guaranteed to be descent directions. We therefore investigate a symmetrized and PSD-perturbed Hessian approximation method for multisecant QN. We offer an efficiently computable method for producing the PSD perturbation, show superlinear convergence of the new method, and demonstrate improved numerical experiments over general convex minimization problems. We also investigate the limited memory extension of the method, focusing on BFGS, on both convex and non-convex functions. Our results suggest that in ill-conditioned optimization landscapes, leveraging multiple secants can accelerate convergence and yield higher-quality solutions compared to traditional single-secant methods.

math.OC↗

arXiv2025

Technical Overview of Recent Developments in Small Modular Reactors in the United States

Small modular reactors (SMRs) are a class of advanced nuclear fission reactors characterized by their compact core size (typically <300 MWe) and passive safety systems. Their modular design enables on-site assembly, making them suitable for deployment in locations inaccessible to conventional large-scale reactors. With rising global energy demand, particularly driven by the growth of AI, SMRs have recently gained attention as a potential solution for powering data centers. This technical review aims to provide the public and relevant stakeholders with a foundational understanding of SMR technology. It begins with an overview of SMR concepts, historical context, and their current role in the U.S. energy mix. Detailed technical summaries of nine selected SMR designs are then presented, covering core design, fuel systems, reactivity control, and safety features. The report also outlines key regulatory frameworks, including 10 CFR Part 50, Part 52, and the technology-inclusive, risk-informed, and performance-based framework currently under development. Finally, major U.S. programs and legislative efforts supporting SMR deployment over the past decade are summarized.

physics.soc-ph↗

arXiv2025

The Emperor's New Clothes in Benchmarking? A Rigorous Examination of Mitigation Strategies for LLM Benchmark Data Contamination

Benchmark Data Contamination (BDC)-the inclusion of benchmark testing samples in the training set-has raised increasing concerns in Large Language Model (LLM) evaluation, leading to falsely inflated performance estimates and undermining evaluation reliability. To address this, researchers have proposed various mitigation strategies to update existing benchmarks, including modifying original questions or generating new ones based on them. However, a rigorous examination of the effectiveness of these mitigation strategies remains lacking. In this paper, we design a systematic and controlled pipeline along with two novel metrics-fidelity and contamination resistance-to provide a fine-grained and comprehensive assessment of existing BDC mitigation strategies. Previous assessment methods, such as accuracy drop and accuracy matching, focus solely on aggregate accuracy, often leading to incomplete or misleading conclusions. Our metrics address this limitation by emphasizing question-level evaluation result matching. Extensive experiments with 10 LLMs, 5 benchmarks, 20 BDC mitigation strategies, and 2 contamination scenarios reveal that no existing strategy significantly improves resistance over the vanilla case (i.e., no benchmark update) across all benchmarks, and none effectively balances fidelity and contamination resistance. These findings underscore the urgent need for designing more effective BDC mitigation strategies. Our code repository is available at https://github.com/ASTRAL-Group/BDC_mitigation_assessment.

cs.AI↗

arXiv2025

Enhanced Predictive Capability for Chaotic Dynamics by Modified Quantum Reservoir Computing

Deducing the states of spatiotemporally chaotic systems (SCSs) as they evolve in time is crucial for various applications. However, it is a dramatic challenge for generally achieving so due to the complexity of non-periodic dynamics and the hardness of obtaining robust solutions. In recent, there is a growing interest in approaching the problem using both classical and quantum machine learning methods. Although effective for predicting SCSs within a relative short time, the current schemes are not capable of providing robust solutions for longer time than training time. Here, we propose an approach for advancing the prediction of chaotic behavior. Our approach can be viewed as a novel quantum reservoir computing scheme, which can simultaneously capture the linear and the nonlinear features of input data and evolve under a modified Hamiltonian. Our work paves the way for a new avenue in handling SCSs.

quant-ph↗

arXiv2025

Quantum Next-Generation Reservoir Computing and Its Quantum Optical Implementation

Quantum reservoir computing (QRC) exploits the information-processing capabilities of quantum systems to tackle time-series forecasting tasks, which is expected to be superior to their classical counterparts. By far, many QRC schemes have been theoretically proposed. However, most of these schemes involves long-time evolution of quantum systems or networks with quantum gates. This poses a challenge for practical implementation of these schemes, as precise manipulation of quantum systems is crucial, and this level of control is currently hard to achieve with the existing state of quantum technology. Here, we propose a different way of QRC scheme, which is friendly to experimental realization. It implements the quantum version of nonlinear vector autoregression, extracting linear and nonlinear features of quantum data by measurements. Thus, the evolution of complex networks of quantum gates can be avoided. Compared to other QRC schemes, our proposal also achieves an advance by effectively reducing the necessary training data for reliable predictions in time-series forecasting tasks. Furthermore, we experimentally verify our proposal by performing the forecasting tasks, and the observation matches well with the theorectial ones. Our work opens up a new way toward complex tasks to be solved by using the QRC, which can herald the next generation of the QRC.

quant-ph↗

arXiv2025

Bistable soliton optical frequency combs in a second harmonic generation Kerr cavity

We study the dynamics and stability of soliton optical frequency comb generation in a dissipative, coherently pumped cavity with both second and third-order nonlinearity. Cavity sweep simulations and linear stability analysis based on path continuation reveal the existence of bistable solitons. These families of solutions represent a continuous transition between a purely quadratic and a Kerr cavity soliton frequency comb. Perspective demonstrations of these novel optical sources is an ongoing relevant subject within the frequency comb community.

nlin.CD↗

arXiv2025

Likelihood-based Nonparametric Receiver Operating Characteristic Curve Analysis in the Presence of Imperfect Reference Standard

In diagnostic studies, researchers frequently encounter imperfect reference standards with some misclassified labels. Treating these as gold standards can bias receiver operating characteristic (ROC) curve analysis. To address this issue, we propose a novel likelihood-based method under a nonparametric density ratio model. This approach enables the reliable estimation of the ROC curve, area under the curve (AUC), partial AUC, and Youden's index with favorable statistical properties. To implement the method, we develop an efficient expectation-maximization algorithm algorithm. Extensive simulations evaluate its finite-sample performance, showing smaller mean squared errors in estimating the ROC curve, partial AUC, and Youden's index compared to existing methods. We apply the proposed approach to a malaria study.

stat.ME↗

arXiv2025

Engineering topological states and quantum-inspired information processing using classical circuits

Based on the correspondence between circuit Laplacian and Schrodinger equation, recent investigations have shown that classical electric circuits can be used to simulate various topological physics and the Schrodinger's equation. Furthermore, a series of quantum-inspired information processing have been implemented by using classical electric circuit networks. In this review, we begin by analyzing the similarity between circuit Laplacian and lattice Hamiltonian, introducing topological physics based on classical circuits. Subsequently, we provide reviews of the research progress in quantum-inspired information processing based on the electric circuit, including discussions of topological quantum computing with classical circuits, quantum walk based on classical circuits, quantum combinational logics based on classical circuits, electric-circuit realization of fast quantum search, implementing unitary transforms and so on.

cond-mat.mes-hall↗

arXiv2025

Real-time Estimation of DoS Duration and Frequency for Security Control

In this paper, we develop a new denial-of-service (DoS) estimator, enabling defenders to identify duration and frequency parameters of any DoS attacker, except for three edge cases, exclusively using real-time data. The key advantage of the estimator lies in its capability to facilitate security control in a wide range of practical scenarios, even when the attacker's information is previously unknown. We demonstrate the advantage and application of our new estimator in the context of two classical control scenarios, namely consensus of multi-agent systems and impulsive stabilization of nonlinear systems, for illustration.

eess.SY↗

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

Dexterous Safe Control for Humanoids in Cluttered Environments via Projected Safe Set Algorithm

It is critical to ensure safety for humanoid robots in real-world applications without compromising performance. In this paper, we consider the problem of dexterous safety, featuring limb-level geometry constraints for avoiding both external and self-collisions in cluttered environments. Compared to safety with simplified bounding geometries in sprase environments, dexterous safety produces numerous constraints which often lead to infeasible constraint sets when solving for safe robot control. To address this issue, we propose Projected Safe Set Algorithm (p-SSA), an extension of classical safe control algorithms to multi-constraint cases. p-SSA relaxes conflicting constraints in a principled manner, minimizing safety violations to guarantee feasible robot control. We verify our approach in simulation and on a real Unitree G1 humanoid robot performing complex collision avoidance tasks. Results show that p-SSA enables the humanoid to operate robustly in challenging situations with minimal safety violations and directly generalizes to various tasks with zero parameter tuning.

cs.RO↗

arXiv2025

Proximal Flow Inspired Multi-Step Methods

We investigate a family of approximate multi-step proximal point methods, framed as implicit linear discretizations of gradient flow. The resulting methods are multi-step proximal point methods, with similar computational cost in each update as the proximal point method. We explore several optimization methods where applying an approximate multistep proximal points method results in improved convergence behavior. We also include convergence analysis for the proposed method in several problem settings: quadratic problems, general problems that are strongly or weakly (non)convex, and accelerated results for alternating projections.

math.OC↗

arXiv2025

Spatial Temporal Attention based Target Vehicle Trajectory Prediction for Internet of Vehicles

Forecasting vehicle behavior within complex traffic environments is pivotal within Intelligent Transportation Systems (ITS). Though this technology plays a significant role in alleviating the prevalent operational difficulties in logistics and transportation systems, the precise prediction of vehicle trajectories still poses a substantial challenge. To address this, our study introduces the Spatio Temporal Attention-based methodology for Target Vehicle Trajectory Prediction (STATVTPred). This approach integrates Global Positioning System(GPS) localization technology to track target movement and dynamically predict the vehicle's future path using comprehensive spatio-temporal trajectory data. We map the vehicle trajectory onto a directed graph, after which spatial attributes are extracted via a Graph Attention Networks(GATs). The Transformer technology is employed to yield temporal features from the sequence. These elements are then amalgamated with local road network structure maps to filter and deliver a smooth trajectory sequence, resulting in precise vehicle trajectory prediction.This study validates our proposed STATVTPred method on T-Drive and Chengdu taxi-trajectory datasets. The experimental results demonstrate that STATVTPred achieves 6.38% and 10.55% higher Average Match Rate (AMR) than the Transformer model on the Beijing and Chengdu datasets, respectively. Compared to the LSTM Encoder-Decoder model, STATVTPred boosts AMR by 37.45% and 36.06% on the same datasets. This is expected to establish STATVTPred as a new approach for handling trajectory prediction of targets in logistics and transportation scenarios, thereby enhancing prediction accuracy.

cs.RO↗