arXiv subjects

Jun-Jie Zhang

Publications and source records attributed to Jun-Jie Zhang.

At least 19 recordsLinked to original sources

arXiv2026

Autferroics-based true random number generators with enhanced performance

Physical entropy-driven true random number generators are essential for emerging probabilistic computing paradigms, but conventional implementations based on magnetic tunneling junctions have reached their performance plateaus limited by inherent tradeoffs and weak tunability. Here, autferroics, a sister branch of multiferroics, is proposed to construct true random number generators. Benefiting from its unique energy landscape due to strong seesaw-type magnetoelectricity, the performance of true random number generation can be significantly enhanced in autferroic tunneling junctions, verified by passing standard statistical tests. Furthermore, autferroics-based random number generators can exhibit multi-field tunability and intrinsic multi-state randomness, opening an avenue for efficient hardware realization of the complex-number arithmetic and simulation of probability distributions of quantum mixed states within stochastic circuits.

cond-mat.mtrl-sci↗

arXiv2026

Physics-Informed Neural Network with Squeeze-Excitation-like Attention

We introduce SEA-PINN, a novel architecture that incorporates a Squeeze-Excitation-like attention mechanism into physics-informed neural networks to dynamically recalibrate the importance of neurons across layers. A key feature of SEA-PINN is its highly stable initialization. On 17 out of 20 benchmark problems, SEA-PINN exhibit nearly negligible variance and significantly reduced initial loss, establishing a quasi-deterministic and favorable starting point for optimization. Notably, without employing Fourier feature embeddings or periodic activation functions, SEA-PINN attained competitive accuracy (83\% vs. 90\% improvement relative to FNN-PINN on the high-frequency case 7) as compared with TSA-PINN-a model specifically engineered for high-frequency problems via learnable frequencies in sinusoidal activations. Furthermore, integrating SEA-PINN into TSA-PINN boosted performance by 42.49\%. These results underscore SEA-PINN as a lightweight plug-in module that enhances nonlinear representation power, promotes more robust and efficient convergence, and strengthens the overall reliability of physics-informed learning.

cs.LG↗

arXiv2026

Neural Uncertainty Principle: A Unified View of Adversarial Fragility and LLM Hallucination

Adversarial vulnerability in vision and hallucination in large language models are conventionally viewed as separate problems, each addressed with modality-specific patches. This study first reveals that they share a common geometric origin: the input and its loss gradient are conjugate observables subject to an irreducible uncertainty bound. Formalizing a Neural Uncertainty Principle (NUP) under a loss-induced state, we find that in near-bound regimes, further compression must be accompanied by increased sensitivity dispersion (adversarial fragility), while weak prompt-gradient coupling leaves generation under-constrained (hallucination). Crucially, this bound is modulated by an input-gradient correlation channel, captured by a specifically designed single-backward probe. In vision, masking highly coupled components improves robustness without costly adversarial training; in language, the same prefill-stage probe detects hallucination risk before generating any answer tokens. NUP thus turns two seemingly separate failure taxonomies into a shared uncertainty-budget view and provides a principled lens for reliability analysis. Guided by this NUP theory, we propose ConjMask (masking high-contribution input components) and LogitReg (logit-side regularization) to improve robustness without adversarial training, and use the probe as a decoding-free risk signal for LLMs, enabling hallucination detection and prompt selection. NUP thus provides a unified, practical framework for diagnosing and mitigating boundary anomalies across perception and generation tasks.

cs.LG↗

arXiv2026

A Geometric Probe of the Accuracy-Robustness Trade-off: Sharp Boundaries in Symmetry-Breaking Dimensional Expansion

The trade-off between clean accuracy and adversarial robustness is a pervasive phenomenon in deep learning, yet its geometric origin remains elusive. In this work, we utilize Symmetry-Breaking Dimensional Expansion (SBDE) as a controlled probe to investigate the mechanism underlying this trade-off. SBDE expands input images by inserting constant-valued pixels, which breaks translational symmetry and consistently improves clean accuracy (e.g., from $90.47\%$ to $95.63\%$ on CIFAR-10 with ResNet-18) by reducing parameter degeneracy. However, this accuracy gain comes at the cost of reduced robustness against iterative white-box attacks. By employing a test-time \emph{mask projection} that resets the inserted auxiliary pixels to their training values, we demonstrate that the vulnerability stems almost entirely from the inserted dimensions. The projection effectively neutralizes the attacks and restores robustness, revealing that the model achieves high accuracy by creating \emph{sharp boundaries} (steep loss gradients) specifically along the auxiliary axes. Our findings provide a concrete geometric explanation for the accuracy-robustness paradox: the optimization landscape deepens the basin of attraction to improve accuracy but inevitably erects steep walls along the auxiliary degrees of freedom, creating a fragile sensitivity to off-manifold perturbations.

cs.LG↗

arXiv2026

Hardware-Friendly Input Expansion for Accelerating Function Approximation

One-dimensional function approximation is a fundamental problem in scientific computing and engineering applications. While neural networks possess powerful universal approximation capabilities, their optimization process is often hindered by flat loss landscapes induced by parameter-space symmetries, leading to slow convergence and poor generalization, particularly for high-frequency components. Inspired by the principle of \emph{symmetry breaking} in physics, this paper proposes a hardware-friendly approach for function approximation through \emph{input-space expansion}. The core idea involves augmenting the original one-dimensional input (e.g., $x$) with constant values (e.g., $π$) to form a higher-dimensional vector (e.g., $[π, π, x, π, π]$), effectively breaking parameter symmetries without increasing the network's parameter count. We evaluate the method on ten representative one-dimensional functions, including smooth, discontinuous, high-frequency, and non-differentiable functions. Experimental results demonstrate that input-space expansion significantly accelerates training convergence (reducing LBFGS iterations by 12\% on average) and enhances approximation accuracy (reducing final MSE by 66.3\% for the optimal 5D expansion). Ablation studies further reveal the effects of different expansion dimensions and constant selections, with $π$ consistently outperforming other constants. Our work proposes a low-cost, efficient, and hardware-friendly technique for algorithm design.

cs.LG↗

arXiv2025

Deciphering the lattice vibrational behaviors of CuInP2S6 by angle-resolved polarized Raman scattering

The layered van der Waals (vdW) ferroelectric CuInP2S6 (CIPS) exhibits unique cation hopping-driven phenomena that bring about unconventional properties with intriguing mechanisms and hold promises for advanced applications in nanoelectronics. However, an explicit analysis of its lattice dynamics and vibrational symmetries, pivotal for understanding the material's peculiar ferroelectric and ferroionic behaviors, remains incomplete. Here, we employ angle-resolved polarized Raman spectroscopy in concert with first-principles calculations to systematically unravel the anisotropic lattice vibrations of CIPS single crystals. By analyzing the polarization-dependent Raman intensities, we determine the symmetry assignments and Raman tensors of all major vibrational modes, revealing good agreement with theoretical predictions. Furthermore, we demonstrate the utility of Raman spectroscopy as a sensitive and non-invasive probe for structural and ferroelectric order evolution, by examining temperature-driven phase transitions and thickness-dependent polarization suppression in CIPS. Our findings establish a foundational framework for correlating lattice dynamics with functional properties in CIPS and provide a methodological blueprint for studying other vdW ferroelectrics.

cond-mat.mtrl-sci↗

arXiv2025

Autferroicity: concept, candidates, and applications

Autferroicity is a newly proposed form of hybrid ferroicity, which is a sister branch of multiferroicity. It is characterized by the mutually exclusive magnetic and polar phases within a single system, giving a unique seesaw-type magnetoelectric coupling. This perspective provides a theoretical overview of its underlying concept, phase diagram characteristics, and representative candidates such as Ti-based trichalcogenide monolayers, while also highlighting its potential applications in nonvolatile memory devices and true random number generation.

cond-mat.mtrl-sci↗

arXiv2025

Effect of Rashba spin-orbit coupling on topological phases in monolayer ZnIn2Te4

The interplay of Rashba and quantum spin Hall effects in non-centrosymmetric systems presents both challenges and opportunities for spintronic applications. While Rashba spin-orbit coupling can disrupt the quantum spin Hall phase, their coexistence may enable additional spintronic functionalities by coupling spin-momentum locking in the bulk with topologically protected edge states. Using the ZnIn$_2$Te$_4$ monolayer as a case study-a predicted polar two-dimensional topological insulator-we investigate how intrinsic and Rashba spin-orbit coupling compete within a single material. Our results identify key conditions under which sizable Rashba spin splitting can coexist with a stable quantum spin Hall phase, offering guidance for engineering quantum spin Hall insulators with enhanced spintronic capabilities.

cond-mat.mes-hall↗

arXiv2025

Landau theory description of autferroicity

Autferroics, recently proposed as a sister branch of multiferroics, exhibit strong intrinsic magnetoelectricity, but ferroelectricity and magnetism are mutually exclusive rather than coexisting. Here, a general model is considered based on the Landau theory, to clarify the distinction between multi and autferroics by qualitative change-rotation in Landau free energy landscape and in particular phase mapping. The TiGeSe$_3$ exemplifies a factual material, whose first-principles computed Landau coefficients predict its autferroicity. Our investigations pave the way for an alternative avenue in the pursuit of intrinsically strong magnetoelectrics.

cond-mat.mtrl-sci↗

arXiv2025

Charge transfer induced insulating state at antiperovskite/perovskite heterointerfaces

Heterointerfaces have been pivotal in unveiling extraordinary interfacial properties and enabling multifunctional material platforms. Despite extensive research on all-oxide interfaces, heterointerfaces between different material classes, such as oxides and nitrides, remain underexplored. Here we present the fabrication of a high-quality Dirac metal antiperovskite Ni3InN, characterized by an extremely low temperature coefficient of resistivity, approximately 1.8*10^-8 Ω*cm/K, over a broad temperature range. Atomically sharp heterointerfaces between Ni3InN and SrVO3 were constructed, revealing intriguing interfacial phenomena. Leveraging layer-resolved scanning transmission electron microscopy and electron energy loss spectroscopy, we identified pronounced charge transfer across the well-ordered interface. Remarkably, this interfacial electron transfer from Ni3InN to SrVO3 induces an insulating interfacial layer and an emergent magnetic moment within the Ni3InN layer, consistent with first-principles calculations. These findings pave the way for novel electronic and spintronic applications by enabling tunable interfacial properties in nitride/oxide systems.

cond-mat.mtrl-sci↗

arXiv2025

Two-dimensional multiferroic NbPc COF with strong magnetoelectric coupling and room-temperature ferroelectricity

The realization of two-dimensional multiferroics offers significant potential for nanoscale device functionality. However, type-I two-dimensional multiferroics with strong magnetoelectric coupling, enabling electric field control of spin, remain scarce. In this study, using density functional theory and Monte Carlo simulations, we predict that the niobium phthalocyanine covalent organic framework (NbPc COF) monolayer exhibits type-I multiferroic behavior, with a ferroelectric transition occurring above room temperature. Remarkably, the strong magnetoelectric coupling in NbPc COF monolayer arises from the same origin of magnetism and ferroelectricity. Our findings offer flexible pathways for the design and development of organic nanoscale multiferroic devices with broad applications.

cond-mat.mtrl-sci↗

arXiv2025

On the uncertainty principle of neural networks

In this study, we explore the inherent trade-off between accuracy and robustness in neural networks, drawing an analogy to the uncertainty principle in quantum mechanics. We propose that neural networks are subject to an uncertainty relation, which manifests as a fundamental limitation in their ability to simultaneously achieve high accuracy and robustness against adversarial attacks. Through mathematical proofs and empirical evidence, we demonstrate that this trade-off is a natural consequence of the sharp boundaries formed between different class concepts during training. Our findings reveal that the complementarity principle, a cornerstone of quantum physics, applies to neural networks, imposing fundamental limits on their capabilities in simultaneous learning of conjugate features. Meanwhile, our work suggests that achieving human-level intelligence through a single network architecture or massive datasets alone may be inherently limited. Our work provides new insights into the theoretical foundations of neural network vulnerability and opens up avenues for designing more robust neural network architectures.

cs.LG↗

arXiv2024

Is AI Robust Enough for Scientific Research?

We uncover a phenomenon largely overlooked by the scientific community utilizing AI: neural networks exhibit high susceptibility to minute perturbations, resulting in significant deviations in their outputs. Through an analysis of five diverse application areas -- weather forecasting, chemical energy and force calculations, fluid dynamics, quantum chromodynamics, and wireless communication -- we demonstrate that this vulnerability is a broad and general characteristic of AI systems. This revelation exposes a hidden risk in relying on neural networks for essential scientific computations, calling further studies on their reliability and security.

cs.LG↗

arXiv2024

Symmetry Breaking in Neural Network Optimization: Insights from Input Dimension Expansion

Understanding the mechanisms behind neural network optimization is crucial for improving network design and performance. While various optimization techniques have been developed, a comprehensive understanding of the underlying principles that govern these techniques remains elusive. Specifically, the role of symmetry breaking, a fundamental concept in physics, has not been fully explored in neural network optimization. This gap in knowledge limits our ability to design networks that are both efficient and effective. Here, we propose the symmetry breaking hypothesis to elucidate the significance of symmetry breaking in enhancing neural network optimization. We demonstrate that a simple input expansion can significantly improve network performance across various tasks, and we show that this improvement can be attributed to the underlying symmetry breaking mechanism. We further develop a metric to quantify the degree of symmetry breaking in neural networks, providing a practical approach to evaluate and guide network design. Our findings confirm that symmetry breaking is a fundamental principle that underpins various optimization techniques, including dropout, batch normalization, and equivariance. By quantifying the degree of symmetry breaking, our work offers a practical technique for performance enhancement and a metric to guide network design without the need for complete datasets and extensive training processes.

cs.LG↗

arXiv2024

Constructing and Evaluating Digital Twins: An Intelligent Framework for DT Development

The development of Digital Twins (DTs) represents a transformative advance for simulating and optimizing complex systems in a controlled digital space. Despite their potential, the challenge of constructing DTs that accurately replicate and predict the dynamics of real-world systems remains substantial. This paper introduces an intelligent framework for the construction and evaluation of DTs, specifically designed to enhance the accuracy and utility of DTs in testing algorithmic performance. We propose a novel construction methodology that integrates deep learning-based policy gradient techniques to dynamically tune the DT parameters, ensuring high fidelity in the digital replication of physical systems. Moreover, the Mean STate Error (MSTE) is proposed as a robust metric for evaluating the performance of algorithms within these digital space. The efficacy of our framework is demonstrated through extensive simulations that show our DT not only accurately mirrors the physical reality but also provides a reliable platform for algorithm evaluation. This work lays a foundation for future research into DT technologies, highlighting pathways for both theoretical enhancements and practical implementations in various industries.

eess.SY↗

arXiv2024

JefiAtten: An Attention Based Neural Network Model for Solving Maxwell's Equations with Charge and Current Sources

We present JefiAtten, a novel neural network model employing the attention mechanism to solve Maxwell's equations efficiently. JefiAtten uses self-attention and cross-attention modules to understand the interplay between charge density, current density, and electromagnetic fields. Our results indicate that JefiAtten can generalize well to a range of scenarios, maintaining accuracy across various spatial distribution and handling amplitude variations. The model showcases an improvement in computation speed after training, compared to traditional integral methods. The adaptability of the model suggests potential for broader applications in computational physics, with further refinements to enhance its predictive capabilities and computational efficiency. Our work is a testament to the efficacy of integrating attention mechanisms with numerical simulations, marking a step forward in the quest for data-driven solutions to physical phenomena.

physics.comp-ph↗

arXiv2024

Sliding-mediated ferroelectric phase transition in CuInP2S6 under pressure

Interlayer stacking order has recently emerged as a unique degree of freedom to control crystal symmetry and physical properties in two-dimensional van der Waals (vdW) materials and heterostructures. By tuning the layer stacking pattern, symmetry-breaking and electric polarization can be created in otherwise non-polar crystals, whose polarization reversal depends on the interlayer sliding motion. Herein, we demonstrate that in a vdW layered ferroelectric, its existing polarization is closely coupled to the interlayer sliding driven by hydrostatic pressure. Through combined structural, electrical, vibrational characterizations, and theoretical calculations, we clearly map out the structural evolution of CuInP2S6 under pressure. A tendency towards a high polarization state is observed in the low-pressure region, followed by an interlayer-sliding-mediated phase transition from a monoclinic to a trigonal phase. Along the transformation pathway, the displacive-instable Cu ion serves as a pivot point that regulates the interlayer interaction in response to external pressure. The rich phase diagram of CuInP2S6, which is enabled by stacking orders, sheds light on the physics of vdW ferroelectricity and opens an alternative route to tailoring long-range order in vdW layered crystals.

cond-mat.mtrl-sci↗

arXiv2024

Quantum-Inspired Analysis of Neural Network Vulnerabilities: The Role of Conjugate Variables in System Attacks

Neural networks demonstrate inherent vulnerability to small, non-random perturbations, emerging as adversarial attacks. Such attacks, born from the gradient of the loss function relative to the input, are discerned as input conjugates, revealing a systemic fragility within the network structure. Intriguingly, a mathematical congruence manifests between this mechanism and the quantum physics' uncertainty principle, casting light on a hitherto unanticipated interdisciplinarity. This inherent susceptibility within neural network systems is generally intrinsic, highlighting not only the innate vulnerability of these networks but also suggesting potential advancements in the interdisciplinary area for understanding these black-box networks.

cs.LG↗