arXiv subjects
Publications and source records attributed to Yunpeng Zhu.
We solve Tingley's problem for Haagerup noncommutative $L_p$-spaces, where $1<p\ne 2<\infty$, which gives an affirmative answer to Mori's problem \cite[Problem~6.3]{Mori}.
Let $\mathcal{M}$ be a factor equipped with a semi-finite faithful normal trace $τ$. Let $E(0,\infty)$ be a symmetrically normed function space and $E(\mathcal{M},τ)$ be the corresponding symmetrically normed operator space. Suppose that $a, b$ are $τ$-measurable operators affiliated with $\mathcal{M}$. It is shown that the range of the multiplication operator $S_{a,b}: x\mapsto axb$ on $\mathcal{M}$ is contained in $E(\mathcal{M}, τ)$ if and only if $μ(a)μ(b)$ belongs to $E(0, \infty)$, where $μ(x)$ stands for the generalized singular value function of a $τ$-measurable operators $x$ affiliated with $\mathcal{M}$. Moreover, we have $$ \|S_{a,b}\|_{\mathcal{M}\to E(\mathcal{M},τ)}= \| μ(a )μ( b) \|_{E (0,\infty) }, $$ which answers a question by Fialkow and Loebl (1984). We also consider the quasi-normed case, and show that the natural quasi-norm of weak $L_p$-space, $0<p<\infty$, is not monotone with respect to the logarithmic submajorisation.
We give an affirmative answer to Tingley's problem for Schatten--von Neumann classes $C_p$ by a unified approach for all $0<p\ne 2<\infty$, extending results due to Fernández-Polo et al.
Vision-Language-Action (VLA) models hold great promise for general-purpose robotic intelligence, yet scaling up such models is severely bottlenecked by the high cost of acquiring annotated training data. Fortunately, vision-equipped robots deployed across various domains already produce abundant vision-action pairs that can be leveraged to scale up VLA training more efficiently. However, these raw data cannot be centrally aggregated due to various constraints and also exhibit severe heterogeneity. To address these challenges, in this paper, we propose ForgeVLA, a federated VLA training framework that learns VLA models from distributed vision-action pairs without centralizing raw data or requiring manual annotations. Specifically, each client in ForgeVLA is equipped with an embodied instruction classifier that maps vision-action pairs to a predefined instruction set, recovering the missing language modality and forming complete vision-language-action triplets. Beyond triplet construction, we also identify vision-language feature collapse as a critical challenge that has been largely overlooked in prior federated VLA research. To mitigate this issue, ForgeVLA combines a client-side contrastive planning loss with a server-side adaptive aggregation strategy to learn task-discriminative representations efficiently. Extensive experiments across multiple benchmarks show that ForgeVLA significantly outperforms other baselines, and ablation studies further validate the contribution of each component.
We present LoRM (Language of Rotating Machinery), a self-supervised framework for multi-modal rotating-machinery signal understanding and real-time condition monitoring. LoRM is built on the idea that rotating-machinery signals can be viewed as a machine language: local signals can be tokenised into discrete symbolic units, and their future evolution can be predicted from observed multi-sensor context. Unlike conventional signal-processing methods that rely on hand-crafted transforms and features, LoRM reformulates multi-modal sensor data as a token-based sequence-prediction problem. For each data window, the observed context segment is retained in continuous form, while the future target segment of each sensing channel is quantised into a discrete token. Then, efficient knowledge transfer is achieved by partially fine-tuning a general-purpose pre-trained language model on industrial signals, avoiding the need to train a large model from scratch. Finally, condition monitoring is performed by tracking token-prediction errors as a health indicator, where increasing errors indicate degradation. In-situ tool condition monitoring (TCM) experiments demonstrate stable real-time tracking and strong cross-tool generalisation, showing that LoRM provides a practical bridge between language modelling and industrial signal analysis. The source code is publicly available at https://github.com/Q159753258/LormPHM.
Experimental Modal Analysis (EMA) has been widely used to identify structural dynamic properties, including natural frequencies, damping ratios, and mode shapes, for structural integrity assessment. The Poly-reference Least Squares Complex Frequency (pLSCF) method is one of the most widely adopted approaches for EMA because of its strong ability to separate closely spaced modes and its robustness to measurement noise. However, pLSCF-based EMA is generally limited to low-dimensional cases with a small number of measurement points, as its computational cost increases rapidly for high-dimensional or continuous structural measurements, particularly with increasing model order. To overcome this limitation, this paper develops a high-dimensional EMA framework based on Dynamic Mode Decomposition with control (DMDc), a powerful data-driven technique originally developed in fluid dynamics, for modal identification under high-dimensional measurement scenarios. Specifically, the relationship between pLSCF and time-delay DMDc is clarified through the discrete state-space representation of the auto-regressive with exogenous inputs (ARX) model for linear systems. By showing that both methods describe the same physical dynamics of the structure, this study provides a physics-based rationale for applying time-delay DMDc to EMA. The capability and advantages of time-delay DMDc for modal parameter identification in both low- and high-dimensional measurements are validated through numerical simulations of a 6-DOF system and experiments on a cantilever beam using a digital camera. The results demonstrate that time-delay DMDc enables robust and reliable modal parameter identification, effectively addressing high-dimensional EMA problems that are difficult for conventional pLSCF and highlighting its potential for real-world structural dynamics applications.
This paper presents UnderwaterVLA, a novel framework for autonomous underwater navigation that integrates multimodal foundation models with embodied intelligence systems. Underwater operations remain difficult due to hydrodynamic disturbances, limited communication bandwidth, and degraded sensing in turbid waters. To address these challenges, we introduce three innovations. First, a dual-brain architecture decouples high-level mission reasoning from low-level reactive control, enabling robust operation under communication and computational constraints. Second, we apply Vision-Language-Action(VLA) models to underwater robotics for the first time, incorporating structured chain-of-thought reasoning for interpretable decision-making. Third, a hydrodynamics-informed Model Predictive Control(MPC) scheme compensates for fluid effects in real time without costly task-specific training. Experimental results in field tests show that UnderwaterVLA reduces navigation errors in degraded visual conditions while maintaining higher task completion by 19% to 27% over baseline. By minimizing reliance on underwater-specific training data and improving adaptability across environments, UnderwaterVLA provides a scalable and cost-effective path toward the next generation of intelligent AUVs.
We introduce a computationally efficient method for the automation of inverse design in science and engineering. Based on simple least-square regression, the underlying dynamic mode decomposition algorithm can be used to construct a low-rank subspace spanning multiple experiments in parameter space. The proposed inverse design dynamic mode composition (ID-DMD) algorithm leverages the computed low-dimensional subspace to enable fast digital design and optimization on laptop-level computing, including the potential to prescribe the dynamics themselves. Moreover, the method is robust to noise, physically interpretable, and can provide uncertainty quantification metrics. The architecture can also efficiently scale to large-scale design problems using randomized algorithms in the ID-DMD. The simplicity of the method and its implementation are highly attractive in practice, and the ID-DMD has been demonstrated to be an order of magnitude more accurate than competing methods while simultaneously being 3-5 orders faster on challenging engineering design problems ranging from structural vibrations to fluid dynamics. Due to its speed, robustness, interpretability, and ease-of-use, ID-DMD in comparison with other leading machine learning methods represents a significant advancement in data-driven methods for inverse design and optimization, promising a paradigm shift in how to approach inverse design in practice.
The incidence and mortality rates of malignant tumors, such as acute leukemia, have risen significantly. Clinically, hospitals rely on cytological examination of peripheral blood and bone marrow smears to diagnose malignant tumors, with accurate blood cell counting being crucial. Existing automated methods face challenges such as low feature expression capability, poor interpretability, and redundant feature extraction when processing high-dimensional microimage data. We propose a novel fine-grained classification model, SCKansformer, for bone marrow blood cells, which addresses these challenges and enhances classification accuracy and efficiency. The model integrates the Kansformer Encoder, SCConv Encoder, and Global-Local Attention Encoder. The Kansformer Encoder replaces the traditional MLP layer with the KAN, improving nonlinear feature representation and interpretability. The SCConv Encoder, with its Spatial and Channel Reconstruction Units, enhances feature representation and reduces redundancy. The Global-Local Attention Encoder combines Multi-head Self-Attention with a Local Part module to capture both global and local features. We validated our model using the Bone Marrow Blood Cell Fine-Grained Classification Dataset (BMCD-FGCD), comprising over 10,000 samples and nearly 40 classifications, developed with a partner hospital. Comparative experiments on our private dataset, as well as the publicly available PBC and ALL-IDB datasets, demonstrate that SCKansformer outperforms both typical and advanced microcell classification methods across all datasets. Our source code and private BMCD-FGCD dataset are available at https://github.com/JustlfC03/SCKansformer.
Hybrid SiN-QD microlasers coupled to a passive SiN output waveguide with 7μm diameter and record low threshold density of 27 μJ cm-2 are demonstrated. A new design and unique processing scheme starting from SiN/QD/SiN stacks offer long term stability and facilitate in depth laser characterization. This approach opens up new paths for optical communication, lab-on-a-chip, gas sensing and, potentially, on-chip cavity quantum electrodynamics and quantum optics.