arXiv subjects

Jianhua Yang

Publications and source records attributed to Jianhua Yang.

At least 19 recordsLinked to original sources

arXiv2026

BIG-CBF: Behavior-Imagination-Guided Control Barrier Function with Shared Uncertainty for Mobile Robot Navigation

Control barrier functions (CBFs) provide a mathematically grounded framework for enforcing local collision-avoidance constraints in autonomous mobile robots, commonly through optimization-based safety filters. However, a minimum-intervention CBF filter lacks task-level maneuver awareness and may fail to select a productive avoidance direction when multiple distinct maneuvers are locally viable, leading to safe but stalled behavior in geometrically ambiguous environments. This paper presents BIG-CBF, Behavior-Imagination-Guided Control Barrier Function with shared uncertainty, a two-rate navigation architecture that separates low-rate maneuver selection from high-rate safety filtering. Over a short horizon, six closed-loop feedback behaviors are imagined and evaluated using analytic CBF compatibility together with a lightweight objective accounting for task progress, freezing, smoothness, and switching. To reduce planning-execution mismatch, the imagination and execution layers share consistent uncertainty sources for relative-motion delay, obstacle prediction, zero-order-hold motion, and command-execution residuals, while a hard CBF remains the final safety authority. In a 3,600-episode comparative benchmark across nine scenarios, BIG-CBF achieves the highest overall task success rate of 99.78% while substantially reducing downstream CBF intervention. On a physical omnidirectional robot with onboard Jetson Orin Nano computation, BIG-CBF completes all 15 evaluation runs without a recorded contact event. Matched hardware comparisons against the non-shared variant further show lower CBF intervention energy and activation frequency, supporting improved consistency between maneuver selection and safety-critical execution.

cs.RO↗

arXiv2026

GuardianBench: A Same-Scene Instruction-Contrastive Benchmark for Latent Contextual Risk in Embodied AI

In embodied AI, safety risk can be latent: a benign instruction and a safe scene become hazardous only when composed. Prior work has advanced embodied safety by varying visual contexts or evaluating execution-time dynamics, but the complementary axis of fixing the scene and varying only the instruction remains underexplored. We introduce GuardianBench, an instruction-contrastive benchmark grounded in international safety standards that isolates this latent contextual risk through 3,024 instruction-scene examples organized as same-scene Safe/Unsafe contrastive pairs across various hazard categories. Benchmarking state-of-the-art vision-language models (VLMs) reveals instruction-insensitive verdicts: models disproportionately approve both instructions under a given scene; across the primary models, average pair accuracy is only 24.1%. Our systematic rationale audit localizes the dominant failure: models fail to bind the instruction-relevant cues that differentiate safe from unsafe compositions. As a post-training case study, Verdict Log-Odds Supervision (VLOS), a lightweight verdict-level objective, substantially improves performance on open-weight backbones. Together, our latent contextual risk task formulation, standards-grounded contrastive benchmark construction, pair-level and rationale-level failure diagnosis, and benchmark-enabled verdict calibration establish GuardianBench as a controlled evaluation suite for exposing and improving safety reasoning over instruction-scene compositions under latent contextual risk.

cs.AI↗

arXiv2026

Visible-Light Imaging Diagnosis of Neutral Particle Emission Tomography in the Tokamak Divertor: An Efficient Transformer-based Surrogate Model

Nuclear fusion has made significant progress in recent years and is expected to become one of the most important pathways to addressing global energy challenges. This paper focuses on observing plasma using visible-light cameras, analyzing its spatio-temporal motion cues, and predicting the two-dimensional spatial distribution of light intensity, aiming to provide a foundational basis for future scientific experiments using deep neural networks. Specifically, we propose Delta-InvFormer, a novel backbone network centered on a differential Transformer. The key insight is that by taking consecutive video frames as input, we can better capture the dynamics of the plasma. Moreover, spatial and temporal differential self-attention effectively mitigates interference from noisy signals, ensuring high-quality feature extraction. These features are then fused into a compact and informative representation, which is fed into a decoder network to predict the distribution. Based on real experimental data collected from the Experimental Advanced Superconducting Tokamak (EAST) large-scale scientific facility, our results demonstrate that the proposed model not only significantly accelerates traditional methods for distribution prediction but also achieves competitive reconstruction accuracy. The source code of this paper will be released on https://github.com/Event-AHU/OpenFusion

cs.CV↗

arXiv2026

UESF-Bench: Benchmarking and Probing for Unified Embodied Seeking and Following

Language-guided human following is an important capability for embodied agents, but existing benchmarks typically assume that the target person is visible at the start of an episode. This setting simplifies the problem and overlooks a more realistic requirement: an agent often needs to first find a language-described target and then persistently follow that target in a dynamic environment. While recent work has started to study human search, existing settings are typically evaluated in task-specific scenarios and often rely on stronger prior knowledge of the environment. Moreover, they usually treat searching and following as separate tasks and still lack a unified benchmark for systematic evaluation. To address these limitations, we introduce the Unified Embodied Seeking and Following Benchmark (UESF-Bench), a large-scale and diverse benchmark for embodied human seeking and following. The benchmark requires agents to handle semantic-guided exploration, reliable behavior switching and recovery, and delayed identity grounding. To this end, we propose SeekFollow-VLA, a vision-language-action framework with a task-driven routing mechanism for latent phase inference and transition modeling between seeking and following. Experimental results show that SeekFollow-VLA achieves clear improvements over both single-head and dual-head baselines across single-person and multi-person environments, establishing a baseline for unified embodied seek-and-follow.

cs.AI↗

arXiv2026

FlowWAM: Optical Flow as a Unified Action Representation for World Action Models

World Action Models (WAMs) are able to leverage pretrained video generators for both world modeling and action prediction. However, directly leveraging such video generators for control raises a new challenge: how to represent actions in a suitable form that aligns with pretrained video generators while carrying enough motion cues for accurate control. Existing numerical actions fail to satisfy the former, and prior visual action representations overlook the temporal motion structure across frames. We address this issue with FlowWAM, a dual-stream diffusion framework that adopts optical flow as a unified, video-native action representation. Flow videos share the same format as RGB videos and encode rich per-pixel displacement. By jointly modeling them within a shared pretrained video generator, FlowWAM can naturally implement two modes of WAMs. In policy mode, FlowWAM generates flow for action prediction, while in world-model mode, it uses target flow sequences to guide future video generation. Moreover, since flow can be easily extracted from raw videos without action labels, FlowWAM can leverage large-scale action-unlabeled video datasets for pretraining. We empirically find that our flow-based action representation delivers gains across both modes. On RoboTwin manipulation, FlowWAM raises the success rate to 92.94% on the Clean setting and 92.14% on Random, outperforming both VLA and WAM baselines. On WorldArena world modeling, it achieves the best overall EWMScore (63.71) with an 18.4% relative improvement in trajectory accuracy. More results can be found on our project website: https://flow-wam.github.io .

cs.RO↗

arXiv2026

PIER-Flow: Physics-Informed Efficient Rectified Flow for Real-Time Mobile Robot Navigation

Autonomous navigation in dense and highly dynamic environments requires both physically feasible control and low-latency replanning. Optimization-based methods such as Model Predictive Control (MPC) explicitly handle robot kinematics and safety constraints, but repeated nonlinear optimization can limit real-time responsiveness. Deterministic behavior-cloning policies enable efficient inference but may fail to represent multimodal avoidance behaviors, whereas diffusion policies capture multimodality at the cost of time-consuming iterative denoising. We propose PIER-Flow (Physics-Informed Efficient Rectified Flow), a lightweight navigation policy for mobile robots. By distilling an MPC expert into a continuous-time Ordinary Differential Equation (ODE), PIER-Flow achieves single-step action generation through parallel latent sampling and lightweight feasibility selection. We introduce a physics-informed training objective to enforce kinematic consistency, paired with an asynchronous action chunking architecture for robust sim-to-real deployment. Extensive simulations demonstrate that PIER-Flow achieves a 98.85\% success rate and zero collisions, with an average inference of $\sim$1.29 ms, which accelerates planning by 37.2$\times$ compared to MPC and over 800$\times$ against standard diffusion models. Crucially, real-world deployment on a resource-constrained edge computer further achieves an approximately stable inference latency of $\sim$5.3 ms, avoiding the latency spikes and freezing events observed with planning baselines.

cs.RO↗

arXiv2026

Hierarchical Multi-to-Single-Modal Knowledge Distillation for Disruption Prediction in EAST

Plasma disruption is a critical threat to tokamak safety. Existing data-driven predictors mainly rely on time-series diagnostic signals, while visible images provide complementary spatial cues including plasma deformation, local brightening, and radiation-structure evolution. Although the image modality improves the model's discriminative capability, it also substantially increases the computational cost during inference. To address this issue, we propose a hierarchical multi-to-single-modal knowledge distillation framework for disruption prediction on a synchronized EAST multimodal dataset. During training, visible images and time-series signals are used to train a multimodal teacher, which learns disruption precursor representations through Transformer-based encoders and a prototype-guided spatiotemporal hypergraph module. During inference, only the time-series student is retained, with multimodal knowledge transferred through graph-structure-level, representation-level, and decision-level distillation. On the 640-discharge EAST dataset, the results demonstrate that the proposed framework can preserve the discriminative advantages of multimodal learning while substantially reducing inference cost, and providing an effective route for efficient disruption prediction in EAST. The source code of this paper will be released on https://github.com/Event-AHU/OpenFusion.

cs.CV↗

arXiv2026

Multi-Level Barriers to Generative AI Adoption Across Disciplines and Professional Roles in Higher Education

Generative Artificial Intelligence (GenAI) is rapidly reshaping higher education, yet barriers to its adoption across different disciplines and institutional roles remain underexplored. Existing literature frequently attributes adoption barriers to individual-level factors such as perceived usefulness and ease of use. This study instead investigates whether such barriers are structurally produced. Drawing on a multi-method survey analysis of 272 academic and professional services (PSs) staff at a Russell Group university, we examine how disciplinary contexts and institutional roles shape perceived barriers. By integrating multinomial logistic regression (MLR), structural equation modelling (SEM), and semantic clustering of open-ended responses, we move beyond descriptive accounts to provide a multi-level explanation of GenAI adoption. Our findings reveal clear, systematic differences: non-STEM academics primarily report ethical and cultural barriers related to academic integrity, whereas STEM and PSs staff disproportionately emphasize institutional, governance, and infrastructure constraints. We conclude that GenAI adoption barriers are deeply embedded in organizational ecosystems and epistemic norms, suggesting that universities must move beyond generalized training to develop role-specific governance and support frameworks.

cs.CY↗

arXiv2026

AI-Driven Contribution Evaluation and Conflict Resolution: A Framework & Design for Group Workload Investigation

The equitable assessment of individual contribution in teams remains a persistent challenge, where conflict and disparity in workload can result in unfair performance evaluation, often requiring manual intervention - a costly and challenging process. We survey existing tool features and identify a gap in conflict resolution methods and AI integration. To address this, we propose a framework and implementation design for a novel AI-enhanced tool that assists in dispute investigation. The framework organises heterogeneous artefacts - submissions (code, text, media), communications (chat, email), coordination records (meeting logs, tasks), peer assessments, and contextual information - into three dimensions with nine benchmarks: Contribution, Interaction, and Role. Objective measures are normalised, aggregated per dimension, and paired with inequality measures (Gini index) to surface conflict markers. A Large Language Model (LLM) architecture performs validated and contextual analysis over these measures to generate interpretable and transparent advisory judgments. We argue for feasibility under current statutory and institutional policy, and outline practical analytics (sentimental, task fidelity, word/line count, etc.), bias safeguards, limitations, and practical challenges.

cs.AI↗

arXiv2026

Disorder effect on the superfluid density and the origin of the pseudogap end point in the cuprate superconductors

A major puzzle in the study of the cuprate superconductivity is the origin of the pseudogap end point. Intriguingly, such a critical doping is also where the superfluid density of the system reaches its maximum. A non-monotonic doping dependence of the superfluid density is rather unusual since the Drude weight of the cuprate system is found to increase monotonically with the doping concentration. It is generally believed that such a peculiar behavior should be attributed to both the strongly correlated nature of the cuprate system and the disorder effect. In this work, we develop a variational theory for the zero temperature superfluid density of the disordered $t-J$ model. This is achieved in two steps. First, we perform an unrestricted variational optimization of an RVB variational ground state for the disordered $t-J$ model. Second, we construct the variational state that describes the paramagnetic current response on such an RVB state. The zero temperature superfluid density $ρ_{s}(0)$ is then extracted from the curvature of the variational ground state energy of the system as a function of the external electromagnetic field. We find that $ρ_{s}(0)$ computed in this way is remarkably robust against the disorder effect. More specifically, we find that $ρ_{s}(0)$ is a monotonically increasing function of doping concentration $x$ and scales linearly with the total optical weight. This is consistent with the observation in the underdoped cuprates but is strongly at odd with the behavior in the overdoped cuprates. The strong contrast between the disorder effect in the underdoped and the overdoped regime lends strong support to our previous proposal that there exist a Mott transition between a doped-Mott-insulating metal in the underdoped regime and a fermi-liquid-like metal in the overdoped regime around the pseudogap end point.

cond-mat.supr-con↗

arXiv2026

Vibrational resonance in a frequency-adaptive learning Duffing system

Vibrational resonance focuses on the resonance behavior of a nonlinear system when it is subjected to both a weak low-frequency characteristic signal and a high-frequency auxiliary signal. A traditional Duffing system has a fixed natural frequency and lacks adaptability to the excitation frequency, resulting in vibrational resonance occurring only in a lower frequency range, which affects the application of vibrational resonance. We propose a frequency-adaptive learning Duffing system to overcome the above problem through a learning rule of the natural frequency. The optimal vibrational resonance performance is demonstrated by examining the influence of auxiliary signal parameters, nonlinear stiffness coefficient and the learning rule on the response. The appearance of vibrational resonance is verified by numerical simulation, approximated theoretical predication and circuit simulation. In addition, the advantages of the proposed frequency-adaptive learning rule are highlighted in vibrational resonance performance by comparing with that of two other commonly used alternatives called Hebbian learning rules. The proposed learning rule makes the system more stable and have a stronger resonance degree. The results provide a useful reference for optimizing nonlinear system response and also for processing a weak characteristic signal through nonlinear resonance methods. These achievements provide a groundbreaking foundation for future applied studies especially in the field of weak and complex signal processing.

nlin.AO↗

arXiv2026

Vibrational resonance in coupled self-learning Duffing oscillators and its application in noisy radio frequency signal processing

This work presents a new coupled array of frequency-adaptive Duffing oscillators. Based on learning rules, the natural frequency of each oscillator changes with the external excitation to achieve the frequency-adaptive capability in the response. The frequency range of vibrational resonance in the response is greatly extended through the frequency-adaptive learning rule. Moreover, the theoretical condition for vibrational resonance is derived and its validity is verified numerically. The coupled self-learning Duffing oscillators can also perform signal denoising in strong noise environment, and its performance in signal denoising has been verified through processing the simulated signal and the wireless radio frequency signal under two scenarios. The superiority of vibrational resonance to the conventional denosing methods such as wavelet transform and Kalman filter has also been illustrated by experimental radio frequency signal processing. The combination of broadband frequency adaptability and strong noise-reduction capability suggests that these oscillators hold considerable potential for engineering applications.

nlin.AO↗

arXiv2025

Frequency-domain Multi-modal Fusion for Language-guided Medical Image Segmentation

Automatically segmenting infected areas in radiological images is essential for diagnosing pulmonary infectious diseases. Recent studies have demonstrated that the accuracy of the medical image segmentation can be improved by incorporating clinical text reports as semantic guidance. However, the complex morphological changes of lesions and the inherent semantic gap between vision-language modalities prevent existing methods from effectively enhancing the representation of visual features and eliminating semantically irrelevant information, ultimately resulting in suboptimal segmentation performance. To address these problems, we propose a Frequency-domain Multi-modal Interaction model (FMISeg) for language-guided medical image segmentation. FMISeg is a late fusion model that establishes interaction between linguistic features and frequency-domain visual features in the decoder. Specifically, to enhance the visual representation, our method introduces a Frequency-domain Feature Bidirectional Interaction (FFBI) module to effectively fuse frequency-domain features. Furthermore, a Language-guided Frequency-domain Feature Interaction (LFFI) module is incorporated within the decoder to suppress semantically irrelevant visual features under the guidance of linguistic information. Experiments on QaTa-COV19 and MosMedData+ demonstrated that our method outperforms the state-of-the-art methods qualitatively and quantitatively.

cs.CV↗

arXiv2025

Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation

Image hiding fully explores the hidden potential of deep learning-based models, aiming to conceal image-level messages within cover images and reveal them from stego images to achieve covert communication. Existing hiding schemes are easily detected by the naked eyes or steganalyzers due to the cover type confined to the spatial domain, single-range feature extraction and attacks, and insufficient loss constraints. To address these issues, we propose a multi-range representations-driven adversarial stego generation framework called MRAG for JPEG image hiding. This design stems from the fact that steganalyzers typically combine local-range and global-range information to better capture hidden traces. Specifically, MRAG integrates the local-range characteristic of the convolution and the global-range modeling of the transformer. Meanwhile, a features angle-norm disentanglement loss is designed to launch multi-range representations-driven feature-level adversarial attacks. It computes the adversarial loss between covers and stegos based on the surrogate steganalyzer's classified features, i.e., the features before the last fully connected layer. Under the dual constraints of features angle and norm, MRAG can delicately encode the concatenation of cover and secret into subtle adversarial perturbations from local and global ranges relevant to steganalysis. Therefore, the resulting stego can achieve visual and steganalysis imperceptibility. Moreover, coarse-grained and fine-grained frequency decomposition operations are devised to transform the input, introducing multi-grained information. Extensive experiments demonstrate that MRAG can achieve state-of-the-art performance.

cs.CV↗

arXiv2025

Using Code Snippets to Teach Programming Languages

Coding is a fundamental skill required in the engineering discipline, and much work exists exploring better ways of teaching coding in the higher education context. In particular, Code Snippets (CSs) are approved to be an effective way of introducing programming language units to students. CSs are portions of source code of varying size and content. They can be used in a myriad of ways, one of which is to teach the code they contain as well as its function. To further explore the use of CSs, a pedagogical summer internship project was set up at the Warwick Manufacturing Group (WMG). The scope of the considerations for the study derives from an educational standpoint. Within the evaluations made, the focus was primarily given to pieces of information which proved to provide evidence pertaining to the methodology involved in either teaching or developing teaching materials. By taking the results produced into account from a pedagogical perspective, it was found that several qualities of popular code snippet tutorials which benefit or hinder the learning process, including code length, interactivity, further support, and quality of explanation. These qualities are then combined and used to present a plan for the design of an effective learning resource which makes use of code snippets.

cs.PL↗

arXiv2025

Stochastic Geometry-Based Performance Evaluation for LEO Satellite-Assisted Space Caching

To achieve the Internet of Things (IoT) vision,Mobile Edge Computing (MEC) is a promising technology aimed at providing low-latency computing services to user equipment (UE). However, terrestrial MEC network struggles to provide service to UEs in remote and maritime region. Low Earth Orbit (LEO) satellite networks have the potential to overcome geographical restrictions and provide seamless global coverage for UEs. In this paper, we provide the first attempt to use stochastic geometry to investigate the performance of implementing space caching with LEO satellites (SATs) in the MEC network. We study a LEO satellite-assisted space caching MEC network, and LEO SATs can be equipped with servers to enable space caching, with the advantage of seamless coverage to assist terrestrial CSs for serving UEs in remote or maritime reigon. Using stochastic geometry and queuing theory, we establish an analytical framework for this MEC network. Meanwhile, we develop association strategies for UEs to connect with LEO SATs or CSs and utilize stochastic geometry to derive uplink and downlink coverage probabilities, considering the diversity of task and service types. On this basis, we employ the queuing theory to calculate the average delay to evaluate the system performance. Through Monte Carlo simulations and numerical results, the system performance is evaluated. The results show the potential of SAT spatial caching in improving the performance of the MEC network. Additionally, our results reveal useful insights such as the significant impact of the altitude and number of LEO SATs on the average delay of the network, providing helpful system-level recommendations for the design and configuration of the space-caching MEC network.

eess.SY↗

arXiv2024

Public Engagement in Action: Developing an Introductory Programming Module for Apprentices

Programming is a crucial skill in today's world and being taught worldwide at different levels. However, in the literature there is little research investigating a formal approach to embedding public engagement into programming module design. This paper explores the integration of public engagement into an introductory programming module, at the University of Warwick, UK, as part of the Digital and Technology Solutions (DTS) degree apprenticeship. The module design follows a 'V' model, which integrates community engagement with traditional programming education, providing a holistic learning experience. The aim is to enhance learning by combining programming education with community engagement. Apprentices participate in outreach activities, teaching programming and Arduino hardware to local secondary school students. This hands-on approach aligns with Kolb's experiential learning model, improving communication skills and solidifying programming concepts through teaching. The module also includes training in safeguarding, presentation skills, and storytelling to prepare apprentices for public engagement. Pedagogical techniques in the module include live coding, group exercises, and Arduino kit usage, as well as peer education, allowing apprentices to learn from and teach each other. Degree apprentices, who balance part-time studies with full-time employment, bring diverse knowledge and motivations. The benefit of public engagement is that it helps bridge their skills gap, fostering teamwork and creating a positive learning environment. Embedding public engagement in programming education also enhances both technical and soft skills, providing apprentices with a deeper understanding of community issues and real-world applications. Our design supports their academic and professional growth, ensuring the module's ongoing success and impact.

cs.CY↗

arXiv2024

Reverse Aperiodic Resonance in Low- to High-Dimensional Bistable Systems: A Complement to Stochastic Resonance Studies in Logic Circuits

As circuits continue to miniaturize, noise has become a significant obstacle to performance optimization. Stochastic resonance in logic circuits offers an innovative approach to harness noise constructively; however, current implementations are limited to basic logical functions such as OR, AND, NOR, and NAND, restricting broader applications. This paper introduces a three-dimensional (3D) coupling model to investigate the counterintuitive phenomena that arise in nonlinear systems under noise. Compared to the one-dimensional Langevin equation and the two-dimensional Duffing equation, the 3D coupling model features more adjustable parameters and coupling interactions, enhancing the system's dynamic behavior. The study demonstrates that increasing noise intensity triggers reverse aperiodic resonance, leading to signal phase reversal and amplitude amplification. This phenomenon is attributed to the motion of Brownian particles in a bistable potential well. Additionally, reverse aperiodic resonance addresses the lack of logical negation in traditional stochastic resonance systems by introducing noise-driven phase reversal, providing a novel alternative to conventional inverters.

nlin.AO↗