arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 415 records · Page 23Linked to original sources

arXiv2025

ControlNeXt: Powerful and Efficient Control for Image and Video Generation

Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.

cs.CV↗

arXiv2025

Realization of a Dirac-vortex topological photonic crystal fiber

Photonic crystal fibers (PCFs) that trap and guide light using photonic bandgaps have revolutionized modern optics with enormous scientific innovations and technological applications spanning many disciplines. Recently, inspired by the discovery of topological phases of matter, Dirac-vortex topological PCFs have been theoretically proposed with intriguing topological properties and unprecedented opportunities in optical fiber communications. However, due to the substantial challenges of fabrication and characterization, experimental demonstration of Dirac-vortex topological PCFs has thus far remained elusive. Here, we report the experimental realization of a Dirac-vortex topological PCF using the standard stack-and-draw fabrication process with silica glass capillaries. Moreover, we experimentally observe that Dirac-vortex single-polarization single-mode bounds to and propagates along the fiber core in the full communication window (1260-1675nm). Our study pushes the research frontier of PCFs and provides a new avenue to enhance their performance and functionality further.

physics.optics↗

arXiv2025

Quantum Geometric Engineering of Dual Hall Effects in 2D Antiferromagnetic Bilayers via Interlayer Magnetic Coupling

The interplay between quantum geometry and magnetic order offers a novel strategy for designing next-generation nanodevices. Here, we demonstrate that interlayer magnetic coupling in two-dimensional (2D) CoPSe3 bilayers enables precise control over quantum geometric mechanisms, unlocking dual intrinsic Hall effects. Our first-principles calculations reveal that the altermagnetic (AM) phase exhibits a giant anisotropic anomalous Hall effect (AHE) ($σ_{xy}$ is approximately 46 S/cm) driven by Berry curvature localized at generic k-points, while the PT-symmetric antiferromagnetic (AFM) phase hosts an intrinsic second-order nonlinear anomalous Hall effect (NAHE) ($χ_{xyy}$ is approximately 160 $μ$S/V) originating from quantum metric accumulation at high-symmetry k-points. By tuning interlayer magnetic couplings, we achieve reversible switching between these phases, leveraging their distinct band structures and symmetry constraints. The Neel-vector-dependent AHE in the AM phase and the symmetry-protected NAHE in the AFM phase highlight quantum geometry as a versatile tool for manipulating transport properties. Our work establishes 2D antiferromagnets as a promising platform for multifunctional device architectures, bridging linear and nonlinear magnetoelectric responses through tailored quantum geometric engineering.

cond-mat.mes-hall↗

arXiv2025

Adversarial Example Based Fingerprinting for Robust Copyright Protection in Split Learning

Currently, deep learning models are easily exposed to data leakage risks. As a distributed model, Split Learning thus emerged as a solution to address this issue. The model is splitted to avoid data uploading to the server and reduce computing requirements while ensuring data privacy and security. However, the transmission of data between clients and server creates a potential vulnerability. In particular, model is vulnerable to intellectual property (IP) infringement such as piracy. Alarmingly, a dedicated copyright protection framework tailored for Split Learning models is still lacking. To this end, we propose the first copyright protection scheme for Split Learning model, leveraging fingerprint to ensure effective and robust copyright protection. The proposed method first generates a set of specifically designed adversarial examples. Then, we select those examples that would induce misclassifications to form the fingerprint set. These adversarial examples are embedded as fingerprints into the model during the training process. Exhaustive experiments highlight the effectiveness of the scheme. This is demonstrated by a remarkable fingerprint verification success rate (FVSR) of 100% on MNIST, 98% on CIFAR-10, and 100% on ImageNet, respectively. Meanwhile, the model's accuracy only decreases slightly, indicating that the embedded fingerprints do not compromise model performance. Even under label inference attack, our approach consistently achieves a high fingerprint verification success rate that ensures robust verification.

cs.CR↗

arXiv2025

Empathy Level Alignment via Reinforcement Learning for Empathetic Response Generation

Empathetic response generation, aiming to understand the user's situation and feelings and respond empathically, is crucial in building human-like dialogue systems. Traditional approaches typically employ maximum likelihood estimation as the optimization objective during training, yet fail to align the empathy levels between generated and target responses. To this end, we propose an empathetic response generation framework using reinforcement learning (EmpRL). The framework develops an effective empathy reward function and generates empathetic responses by maximizing the expected reward through reinforcement learning. EmpRL utilizes the pre-trained T5 model as the generator and further fine-tunes it to initialize the policy. To align the empathy levels between generated and target responses within a given context, an empathy reward function containing three empathy communication mechanisms -- emotional reaction, interpretation, and exploration -- is constructed using pre-designed and pre-trained empathy identifiers. During reinforcement learning training, the proximal policy optimization algorithm is used to fine-tune the policy, enabling the generation of empathetic responses. Both automatic and human evaluations demonstrate that the proposed EmpRL framework significantly improves the quality of generated responses, enhances the similarity in empathy levels between generated and target responses, and produces empathetic responses covering both affective and cognitive aspects.

cs.CL↗

arXiv2025

Gallai-Schur Triples and Related Problems

Schur's Theorem states that, for any $r \in \mathbb{Z}^+$, there exists a minimum integer $S(r)$ such that every $r$-coloring of $\{1,2,\dots,S(r)\}$ admits a monochromatic solution to $x+y=z$. Recently, Budden determined the related Gallai-Schur numbers; that is, he determined the minimum integer $GS(r)$ such that every $r$-coloring of $\{1,2,\dots,GS(r)\}$ admits either a rainbow or monochromatic solution to $x+y=z$. In this article we consider problems that have been solved in the monochromatic setting under a monochromatic-rainbow paradigm. In particular, we investigate Gallai-Schur numbers when $x \neq y$, we consider $x+y+b=z$ and $x+y<z$, and we investigate the asymptotic minimum number of rainbow and monochromatic solutions to $x+y=z$ and $x+y<z$.

math.CO↗

arXiv2025

Internal waves in a 2D subcritical channel

We analyze the scattering of linear internal waves in a two dimensional channel with subcritical bottom topography. We construct the scattering matrix for the internal wave problem in a channel with straight ends, mapping incoming data to outgoing data; this operator turns out to differ by a smoothing operator from the pullback by the ``bounce map'' for boundary data obtained by ray-tracing. As a consequence we obtain unique solvability of the inhomogeneous stationary scattering problem subject to an appropriate outgoing radiation condition.

math.AP↗

arXiv2025

Heat kernels and Green functions for fractional Schrödinger operators with confining potentials

We give two-sided, global (in all variables) estimates of the heat kernel and the Green function of the fractional Schrödinger operator with a non-negative and locally bounded potential $V$ such that $V(x) \to \infty$ as $|x| \to \infty$. We assume that $V$ is comparable to a radial profile with the doubling property. Our bounds are sharp with respect to spatial variables and qualitatively sharp with respect to time. The methods we use combine probabilistic and analytic arguments. They are based on the strong Markov property and the Feynman--Kac formula.

math.PR↗

arXiv2025

General method for calculating transport properties of disordered mesoscopic systems based on the nonequilibrium Green's function formalism

Disorder scattering plays important roles in quantum transport as well as various Hall effects, including the second-order nonlinear Hall effect induced by Berry curvature dipole. Calculation of disorder-averaged transport properties usually requires substantial computational resources, especially for higher-order effects. Existing methods are either limited by approximation conditions or constrained by numerical stability, making it difficult to conveniently obtain average physical quantities over a wide range of disorder strength. In this work, we develop a general method for noninteracting system to obtain analytical expressions of disorder averages in finite orders of disorder strength. This method utilizes the Dyson equation to expand physical quantities expressed in terms of the Green's functions into series of disorder-averaged matrices, and the only approximation involved is the truncation of the Dyson equation. Therefore, this method not only avoids the brute force calculation of disorder samples, but also widely applies to different model systems, types of disorder, and the number of Green's functions in the expressions. We demonstrate the applicability of this general method by calculating averages of the linear conductance of a two-terminal system, the spin Hall conductance and the second-order nonlinear conductance of four-terminal Hall setups. It is found that truncation at the fourth order of disorder strength provides a reasonable accuracy and a convenient Padé treatment effectively extends its applicable range. Numerical results also confirms disorder enhancement of the second-order nonlinear Hall current in four-terminal systems. Moreover, more accurate predictions for a broader range of disorder strength can be achieved by including higher-order terms in a similar manner.

cond-mat.mes-hall↗

arXiv2025

EventEgo3D++: 3D Human Motion Capture from a Head-Mounted Event Camera

Monocular egocentric 3D human motion capture remains a significant challenge, particularly under conditions of low lighting and fast movements, which are common in head-mounted device applications. Existing methods that rely on RGB cameras often fail under these conditions. To address these limitations, we introduce EventEgo3D++, the first approach that leverages a monocular event camera with a fisheye lens for 3D human motion capture. Event cameras excel in high-speed scenarios and varying illumination due to their high temporal resolution, providing reliable cues for accurate 3D human motion capture. EventEgo3D++ leverages the LNES representation of event streams to enable precise 3D reconstructions. We have also developed a mobile head-mounted device (HMD) prototype equipped with an event camera, capturing a comprehensive dataset that includes real event observations from both controlled studio environments and in-the-wild settings, in addition to a synthetic dataset. Additionally, to provide a more holistic dataset, we include allocentric RGB streams that offer different perspectives of the HMD wearer, along with their corresponding SMPL body model. Our experiments demonstrate that EventEgo3D++ achieves superior 3D accuracy and robustness compared to existing solutions, even in challenging conditions. Moreover, our method supports real-time 3D pose updates at a rate of 140Hz. This work is an extension of the EventEgo3D approach (CVPR 2024) and further advances the state of the art in egocentric 3D human motion capture. For more details, visit the project page at https://eventego3d.mpi-inf.mpg.de.

cs.CV↗

arXiv2025

Reconfigurable nonlinear optical computing device for retina-inspired computing

Optical neural networks are at the forefront of computational innovation, utilizing photons as the primary carriers of information and employing optical components for computation. However, the fundamental nonlinear optical device in the neural networks is barely satisfied because of its high energy threshold and poor reconfigurability. This paper proposes and demonstrates an optical sigmoid-type nonlinear computation mode of Vertical-Cavity Surface-Emitting Lasers (VCSELs) biased beneath the threshold. The device is programmable by simply adjusting the injection current. The device exhibits sigmoid-type nonlinear performance at a low input optical power ranging from merely 3-250 μW. The tuning sensitivity of the device to the programming current density can be as large as 15 μW*mm2/mA. Deep neural network architecture based on such device has been proposed and demonstrated by simulation on recognizing hand-writing digital dataset, and a 97.3% accuracy has been achieved. A step further, the nonlinear reconfigurability is found to be highly useful to enhance the adaptability of the networks, which is demonstrated by significantly improving the recognition accuracy by 41.76%, 19.2%, and 25.89% of low-contrast hand-writing digital images under high exposure, low exposure, and high random noise respectively.

physics.optics↗

arXiv2025

Large Negative Magnetoresistance in off-Stochiometric Topological Material PrSbTe

Magnetic topological materials LnSbTe (Ln = lanthanide) have attracted intensive attention because of the presence of interplay between magnetism, topological, and electron correlations depending on the choices of magnetic Ln elements. Varying Sb and Te composition is an efficient approach to control structural, magnetic, and electronic properties. Here we report the composition-dependent properties in PrSbxTe2-x. We identified the tetragonal-to-orthorhombic structure transitions in this material system, and very large negative magnetoresistance in the x = 0.3 composition, which might be ascribed to the coupling between magnetism and transport. Such unusual magnetotransport enables PrSbxTe2-x topological materials as a promising platform for device applications.

cond-mat.mtrl-sci↗

arXiv2025

Distilling Implicit Multimodal Knowledge into Large Language Models for Zero-Resource Dialogue Generation

Integrating multimodal knowledge into large language models (LLMs) represents a significant advancement in dialogue generation capabilities. However, the effective incorporation of such knowledge in zero-resource scenarios remains a substantial challenge due to the scarcity of diverse, high-quality dialogue datasets. To address this, we propose the Visual Implicit Knowledge Distillation Framework (VIKDF), an innovative approach aimed at enhancing LLMs for enriched dialogue generation in zero-resource contexts by leveraging implicit multimodal knowledge. VIKDF comprises two main stages: knowledge distillation, using an Implicit Query Transformer to extract and encode visual implicit knowledge from image-text pairs into knowledge vectors; and knowledge integration, employing a novel Bidirectional Variational Information Fusion technique to seamlessly integrate these distilled vectors into LLMs. This enables the LLMs to generate dialogues that are not only coherent and engaging but also exhibit a deep understanding of the context through implicit multimodal cues, effectively overcoming the limitations of zero-resource scenarios. Our extensive experimentation across two dialogue datasets shows that VIKDF outperforms existing state-of-the-art models in generating high-quality dialogues. The code is available at https://github.com/zhangbo-nlp/VIKDF.

cs.CL↗

arXiv2025

Molecular Odor Prediction Based on Multi-Feature Graph Attention Networks

Olfactory perception plays a critical role in both human and organismal interactions, yet understanding of its underlying mechanisms and influencing factors remain insufficient. Molecular structures influence odor perception through intricate biochemical interactions, and accurately quantifying structure-odor relationships presents significant challenges. The Quantitative Structure-Odor Relationship (QSOR) task, which involves predicting the associations between molecular structures and their corresponding odors, seeks to address these challenges. To this end, we propose a method for QSOR, utilizing Graph Attention Networks to model molecular structures and capture both local and global features. Unlike conventional QSOR approaches reliant on predefined descriptors, our method leverages diverse molecular feature extraction techniques to automatically learn comprehensive representations. This integration enhances the model's capacity to handle complex molecular information, improves prediction accuracy. Our approach demonstrates clear advantages in QSOR prediction tasks, offering valuable insights into the application of deep learning in cheminformatics.

cs.LG↗

arXiv2025

Observation of superconducting pair density modulation within lattice unit cell

In unconventional high-temperature (high-Tc) superconductors, the pair density wave state, an exotic superconducting order showing spatially periodic order parameter modulations with the period of several unit cells and translational symmetry breaking, has attracted broad attention. However, the superconducting pair density modulation within a single unit cell (PDM) has never been carefully investigated before. Here, using scanning tunneling microscopy/spectroscopy, we report the observation of PDM in monolayer high-Tc iron chalcogenide films epitaxially grown on SrTiO3(001). The superconductivity modulations are characterized by the superconducting gap size and the coherence peak sharpness. Further analysis shows that the local maxima and minima in the superconducting gap modulation are centered at the crystallographic locations of the chalcogen atoms, revealing the breaking of the glide-mirror symmetry of the chalcogen atoms in monolayer high-Tc iron chalcogenide films grown on SrTiO3(001). Our findings provide precise microscopic information on superconductivity within the lattice unit cell and may promote the understanding of unconventional high-Tc superconductivity.

cond-mat.supr-con↗

arXiv2025

A Heliocentric-orbiting Objects Processing System (HOPS) for the Wide Field Survey Telescope: Architecture, Processing Workflow, and Preliminary Results

Wide-field surveys have markedly enhanced the discovery and study of solar system objects (SSOs). The 2.5-meter Wide Field Survey Telescope (WFST) represents the foremost facility dedicated to optical time-domain surveys in the northern hemisphere. To fully exploit WFST's capabilities for SSO detection, we have developed a heliocentric-orbiting objects processing system (HOPS) tailored for identifying these objects. This system integrates HelioLinC3D, an algorithm well suited for the WFST survey cadence, characterized by revisiting the same sky field twice on the majority of nights. In this paper, we outline the architecture and processing flow of our SSO processing system. The application of the system to the WFST pilot survey data collected between March and May 2024 demonstrates exceptional performance in terms of both temporal efficiency and completeness. A total of 658,489 observations encompassing 38,520 known asteroids have been documented, and 241 newly discovered asteroids have been assigned provisional designations. In particular, 27% of these new discoveries were achieved using merely two observations per night on three nights. The preliminary results not only illuminate the effectiveness of integrating HelioLinC3D within the SSO processing system, but also emphasize the considerable potential contributions of WFST to the field of solar system science.

astro-ph.IM↗

arXiv2025

Generative AI-driven Cross-layer Covert Communication: Fundamentals, Framework and Case Study

Ensuring end-to-end cross-layer communication security in military networks by selecting covert schemes between nodes is a key solution for military communication security. With the development of communication technology, covert communication has expanded from the physical layer to the network and application layers, utilizing methods such as artificial noise, private networks, and semantic coding to transmit secret messages. However, as adversaries continuously eavesdrop on specific communication channels, the accumulation of sufficient data may reveal underlying patterns that influence concealment, and establishing a cross-layer covert communication mechanism emerges as an effective strategy to mitigate these regulatory challenges. In this article, we first survey the communication security solution based on covert communication, specifically targeting three typical scenarios: device-to-device, private network communication, and public network communication, and analyze their application scopes. Furthermore, we propose an end-to-end cross-layer covert communication scheme driven by Generative Artificial Intelligence (GenAI), highlighting challenges and their solutions. Additionally, a case study is conducted using diffusion reinforcement learning to sovle cloud edge internet of things cross-layer secure communication.

cs.CR↗

arXiv2025

Achieving Network Resilience through Graph Neural Network-enabled Deep Reinforcement Learning

Deep reinforcement learning (DRL) has been widely used in many important tasks of communication networks. In order to improve the perception ability of DRL on the network, some studies have combined graph neural networks (GNNs) with DRL, which use the GNNs to extract unstructured features of the network. However, as networks continue to evolve and become increasingly complex, existing GNN-DRL methods still face challenges in terms of scalability and robustness. Moreover, these methods are inadequate for addressing network security issues. From the perspective of security and robustness, this paper explores the solution of combining GNNs with DRL to build a resilient network. This article starts with a brief tutorial of GNNs and DRL, and introduces their existing applications in networks. Furthermore, we introduce the network security methods that can be strengthened by GNN-DRL approaches. Then, we designed a framework based on GNN-DRL to defend against attacks and enhance network resilience. Additionally, we conduct a case study using an encrypted traffic dataset collected from real IoT environments, and the results demonstrated the effectiveness and superiority of our framework. Finally, we highlight key open challenges and opportunities for enhancing network resilience with GNN-DRL.

cs.CR↗