arXiv subjects

Dan Wang

Publications and source records attributed to Dan Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

Diversity and Interaction Quality of a Heterogeneous Multi-Agent System Applied to a Synchronization Problem

In this paper, scalable controller design to achieve output synchronization for a heterogeneous discrete-time nonlinear multi-agent system is considered. The agents are assumed to exhibit potentially nonlinear dynamics but share linear common oscillatory modes. In a distributed control architecture, scalability is ensured by designing a small number of distinguished controllers, significantly fewer than the number of agents, even when agent diversity is high. Our findings indicate that the number of controllers required can be effectively determined by the number of strongly connected components of the underlying graph. The study in this paper builds on the recently developed phase theory of matrices and systems. First, we employ the concept of matrix phase, specifically the phase alignability of a collection of matrices, to quantify agent diversity. Next, we use matrix phase, particularly the essential phase of the graph Laplacian, to evaluate the interaction quality among the agents. Based on these insights, we derive a sufficient condition for the solvability of the synchronization problem, framed as a trade-off between the agent diversity and the interaction quality. In the process, a controller design procedure based on Lyapunov analysis is provided, which produces low gain, component-wise synchronizing controllers when the solvability condition is satisfied. Numerical examples are given to illustrate the effectiveness of the proposed design procedure. Furthermore, we consider cases where the component-wise controller design problem is unsolvable. We propose alternative strategies involving the design of a small inventory of controllers, which can still achieve synchronization effectively by employing certain clustering methods to manage heterogeneity.

eess.SY↗

arXiv2025

ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction

Pixel-level vision tasks, such as semantic segmentation, require extensive and high-quality annotated data, which is costly to obtain. Semi-supervised semantic segmentation (SSSS) has emerged as a solution to alleviate the labeling burden by leveraging both labeled and unlabeled data through self-training techniques. Meanwhile, the advent of foundational segmentation models pre-trained on massive data, has shown the potential to generalize across domains effectively. This work explores whether a foundational segmentation model can address label scarcity in the pixel-level vision task as an annotator for unlabeled images. Specifically, we investigate the efficacy of using SEEM, a Segment Anything Model (SAM) variant fine-tuned for textual input, to generate predictive masks for unlabeled data. To address the shortcomings of using SEEM-generated masks as supervision, we propose ConformalSAM, a novel SSSS framework which first calibrates the foundation model using the target domain's labeled data and then filters out unreliable pixel labels of unlabeled data so that only high-confidence labels are used as supervision. By leveraging conformal prediction (CP) to adapt foundation models to target data through uncertainty calibration, ConformalSAM exploits the strong capability of the foundational segmentation model reliably which benefits the early-stage learning, while a subsequent self-reliance training strategy mitigates overfitting to SEEM-generated masks in the later training stage. Our experiment demonstrates that, on three standard benchmarks of SSSS, ConformalSAM achieves superior performance compared to recent SSSS methods and helps boost the performance of those methods as a plug-in.

cs.CV↗

arXiv2025

Cascaded frequency conversion of highly charged femtosecond spatiotemporal optical vortices

The degrees of freedom inherent in spatiotemporal optical vortices (STOV's) afford intriguing opportunties to manipulate complex light fields for broad applications such as optical communication, light-matter interactions, particle manipulation, quantum optics, and electron acceleration in the relativistic regime. Unlike previous studies examining the second harmonic generation (SHG) of STOV's having an input topological charge (TC) l^{\left(ω\right)}=1, here we experimentally demonstrate cascaded second and third harmonic generation of STOV's to achieve more diverse wavelength selectivity via sum frequency generation (SFG), achieving unprecedented TC values up to l^{\left(ω\right)}=40. The large TC values are attributed to second (third) harmonic generation of an incident beam satisfying l^{\left(2ω\right)}=2l^{\left(ω\right)} (l^{\left(3ω\right)}=3l^{\left(ω\right)}). What is more, the wavelength of the generated STOV field was found to be tunable by controlling the position of the phase singularity in the frequency domain, and optimizing the nonlinear phase matching condition. Our experimental measurements extend the principle of conservation of the spatiotemporal topological charge to general nonlinear optical parametric processes, suggesting a fundamental approach to the production of STOV fields of arbitrarily large TC and at arbitrary visible wavelengths, and beyond (e.g., the ultraviolet range).

physics.optics↗

arXiv2025

M3-JEPA: Multimodal Alignment via Multi-gate MoE based on the Joint-Embedding Predictive Architecture

Current multimodal learning strategies primarily optimize in the original token space. Such a framework is easy to incorporate with the backbone of pretrained language model, but might result in modality collapse. To alleviate such issues, we leverage the Joint-Embedding Predictive Architecture (JEPA) on the multimodal tasks, which converts the input embedding into the output embedding space by a predictor and then conducts the cross-modal alignment on the latent space. We implement this predictor by a Multi-Gate Mixture of Experts (MMoE) and name the framework as M3-JEPA, accordingly. The gating function disentangles the modality-specific and shared information and derives information-theoretic optimality. The framework is implemented with both contrastive and regularization loss, and solved by alternative gradient descent (AGD) between different multimodal tasks. By thoroughly designed experiments, we show that M3-JEPA can obtain state-of-the-art performance on different modalities and tasks, generalize to unseen datasets and domains, and is computationally efficient in both training and inference. Our observation suggests that M3-JEPA might become a new basis to self-supervised learning in the open world.

cs.LG↗

arXiv2025

T-REX: Mixture-of-Rank-One-Experts with Semantic-aware Intuition for Multi-task Large Language Model Finetuning

Large language models (LLMs) encounter significant adaptation challenges in diverse multitask finetuning. Mixture-of-experts (MoE) provides a promising solution with a dynamic architecture, enabling effective task decoupling. However, scaling up the number of MoE experts incurs substantial parameter and computational overheads and suffers from limited performance gain due to naive routing mechanisms. In this paper, we design a novel framework, mix\underline{\textbf{T}}ure\underline{\textbf{-}}of-\underline{\textbf{R}}ank-on\underline{\textbf{E}}-e\underline{\textbf{X}}perts (\texttt{T-REX}), which leverages the combination of ultra-low rank experts to construct LoRA weights on pretrained LLMs. The rank-1 experts enable a mix-and-match mechanism to quadratically expand the vector subspace of experts with linear parameter overheads, achieving approximate error reduction with optimal efficiency. In addition, T-REX offers implicit guidance to the router, leveraging the inherent semantic clustering of training embeddings as prior knowledge, enabling optimized feature allocation across experts for a smoother convergence. Extensive theoretical and empirical results demonstrate that T-REX achieves superior efficiency and generalizability across diverse tasks. Compared with other LoRA-based methods, T-REX achieves up to 1.78\% mean accuracy improvement with around 30\%-40\% less trainable parameters across 14 public datasets. \href{https://github.com/RoyZry98/T-REX-Pytorch}{Code} is available.

cs.LG↗

arXiv2025

StyleMorpheus: A Style-Based 3D-Aware Morphable Face Model

For 3D face modeling, the recently developed 3D-aware neural rendering methods are able to render photorealistic face images with arbitrary viewing directions. The training of the parametric controllable 3D-aware face models, however, still relies on a large-scale dataset that is lab-collected. To address this issue, this paper introduces "StyleMorpheus", the first style-based neural 3D Morphable Face Model (3DMM) that is trained on in-the-wild images. It inherits 3DMM's disentangled controllability (over face identity, expression, and appearance) but without the need for accurately reconstructed explicit 3D shapes. StyleMorpheus employs an auto-encoder structure. The encoder aims at learning a representative disentangled parametric code space and the decoder improves the disentanglement using shape and appearance-related style codes in the different sub-modules of the network. Furthermore, we fine-tune the decoder through style-based generative adversarial learning to achieve photorealistic 3D rendering quality. The proposed style-based design enables StyleMorpheus to achieve state-of-the-art 3D-aware face reconstruction results, while also allowing disentangled control of the reconstructed face. Our model achieves real-time rendering speed, allowing its use in virtual reality applications. We also demonstrate the capability of the proposed style-based design in face editing applications such as style mixing and color editing. Project homepage: https://github.com/ubc-3d-vision-lab/StyleMorpheus.

cs.CV↗

arXiv2025

A Survey on Federated Analytics: Taxonomy, Enabling Techniques, Applications and Open Issues

The escalating influx of data generated by networked edge devices, coupled with the growing awareness of data privacy, has restricted the traditional data analytics workflow, where the edge data are gathered by a centralized server to be further utilized by data analysts. To continue leveraging vast edge data to support various data-incentive applications, computing paradigms have promoted a transformative shift from centralized data processing to privacy-preserved distributed data processing. The need to perform data analytics on private edge data motivates federated analytics (FA), an emerging technique to support collaborative data analytics among diverse data owners without centralizing the raw data. Despite the wide applications of FA in industry and academia, a comprehensive examination of existing research efforts in FA has been notably absent. This survey aims to bridge this gap by first providing an overview of FA, elucidating key concepts, and discussing its relationship with similar concepts. We then thoroughly examine FA, including its key challenges, taxonomy, and enabling techniques. Diverse FA applications, including statistical metrics, frequency-related applications, database query operations, FL-assisting FA tasks, and other wireless network applications are then carefully reviewed. We complete the survey with several open research issues, future directions, and a comprehensive lessons learned part. This survey intends to provide a holistic understanding of the emerging FA techniques and foster the continued evolution of privacy-preserving distributed data processing in the emerging networked society.

cs.DC↗

arXiv2025

A new look at unitarity in quantization commutes with reduction for toric manifolds

For a symplectic toric manifold we consider half-form quantization in mixed polarizations $\mathcal{P}_\infty$, associated to the action of a subtorus $T^p\subset T^n$. The real directions in these polarizations are generated by components of the $T^p$ moment map. Polarizations of this type can be obtained by starting at a toric Kähler polarization $\mathcal{P}_0$ and then following Mabuchi rays of toric Kähler polarizations generated by the norm square of the moment map of the torus subgroup. These geodesic rays are lifted to the quantum bundle via a generalized coherent state transform (gCST) and define equivariant isomorphisms between Hilbert spaces for the Kähler polarizations and the Hilbert space for the mixed polarization. The polarizations $\mathcal{P}_\infty$ give a new way of looking at the problem of unitarity in the quantization commutes with reduction with respect to the $T^p$-action, as follows. The prequantum operators for the components of the moment map of the $T^p$-action act diagonally with discrete spectrum corresponding to the integral points of the moment polytope. The Hilbert space for the quantization with respect to $\mathcal{P}_\infty$ then naturally decomposes as a direct sum of the Hilbert spaces for all its quantizable coisotropic reductions which, in fact, are the Kähler reductions of the initial Kähler polarization $\mathcal{P}_0$. This will be shown to imply that, for the polarization $\mathcal{P}_\infty$, quantization commutes unitarily with reduction. The problem of unitarity in quantization commutes with reduction for $\mathcal{P}_0$ is then equivalent to the question of whether quantization in the polarization $\mathcal{P}_0$ is unitarily equivalent with quantization in the polarization $\mathcal{P}_\infty$. In fact, this does not hold in general in the toric case.

math.SG↗

arXiv2025

VVRec: Reconstruction Attacks on DL-based Volumetric Video Upstreaming via Latent Diffusion Model with Gamma Distribution

With the popularity of 3D volumetric video applications, such as Autonomous Driving, Virtual Reality, and Mixed Reality, current developers have turned to deep learning for compressing volumetric video frames, i.e., point clouds for video upstreaming. The latest deep learning-based solutions offer higher efficiency, lower distortion, and better hardware support compared to traditional ones like MPEG and JPEG. However, privacy threats arise, especially reconstruction attacks targeting to recover the original input point cloud from the intermediate results. In this paper, we design VVRec, to the best of our knowledge, which is the first targeting DL-based Volumetric Video Reconstruction attack scheme. VVRec demonstrates the ability to reconstruct high-quality point clouds from intercepted transmission intermediate results using four well-trained neural network modules we design. Leveraging the latest latent diffusion models with Gamma distribution and a refinement algorithm, VVRec excels in reconstruction quality, color recovery, and surpasses existing defenses. We evaluate VVRec using three volumetric video datasets. The results demonstrate that VVRec achieves 64.70dB reconstruction accuracy, with an impressive 46.39% reduction of distortion over baselines.

cs.CR↗

arXiv2025

Mitigating Data Scarcity in Time Series Analysis: A Foundation Model with Series-Symbol Data Generation

Foundation models for time series analysis (TSA) have attracted significant attention. However, challenges such as data scarcity and data imbalance continue to hinder their development. To address this, we consider modeling complex systems through symbolic expressions that serve as semantic descriptors of time series. Building on this concept, we introduce a series-symbol (S2) dual-modulity data generation mechanism, enabling the unrestricted creation of high-quality time series data paired with corresponding symbolic representations. Leveraging the S2 dataset, we develop SymTime, a pre-trained foundation model for TSA. SymTime demonstrates competitive performance across five major TSA tasks when fine-tuned with downstream task, rivaling foundation models pre-trained on real-world datasets. This approach underscores the potential of dual-modality data generation and pretraining mechanisms in overcoming data scarcity and enhancing task performance.

cs.LG↗

arXiv2025

Self-adaptive vision-language model for 3D segmentation of pulmonary artery and vein

Accurate segmentation of pulmonary structures iscrucial in clinical diagnosis, disease study, and treatment planning. Significant progress has been made in deep learning-based segmentation techniques, but most require much labeled data for training. Consequently, developing precise segmentation methods that demand fewer labeled datasets is paramount in medical image analysis. The emergence of pre-trained vision-language foundation models, such as CLIP, recently opened the door for universal computer vision tasks. Exploiting the generalization ability of these pre-trained foundation models on downstream tasks, such as segmentation, leads to unexpected performance with a relatively small amount of labeled data. However, exploring these models for pulmonary artery-vein segmentation is still limited. This paper proposes a novel framework called Language-guided self-adaptive Cross-Attention Fusion Framework. Our method adopts pre-trained CLIP as a strong feature extractor for generating the segmentation of 3D CT scans, while adaptively aggregating the cross-modality of text and image representations. We propose a s pecially designed adapter module to fine-tune pre-trained CLIP with a self-adaptive learning strategy to effectively fuse the two modalities of embeddings. We extensively validate our method on a local dataset, which is the largest pulmonary artery-vein CT dataset to date and consists of 718 labeled data in total. The experiments show that our method outperformed other state-of-the-art methods by a large margin. Our data and code will be made publicly available upon acceptance.

cs.CV↗

arXiv2024

Enabling Time-series Foundation Model for Building Energy Forecasting via Contrastive Curriculum Learning

Advances in time-series forecasting are driving a shift from conventional machine learning models to foundation models (FMs) that are trained with generalized knowledge. However, existing FMs still perform poorly in the energy fields, such as building energy forecasting (BEF). This paper studies the adaptation of FM to BEF tasks. We demonstrate the shortcomings of fine-tuning FM straightforwardly from both the perspectives of FM and the data. To overcome these limitations, we propose a new \textit{contrastive curriculum learning}-based training method. Our method optimizes the ordering of training data in the context of TSFM adaptation. Experiments show that our method can improve the zero/few-shot performance by 14.6\% compared to the existing FMs. Our code and new TSFM will be available at .

cs.LG↗

arXiv2024

PolyModel for Hedge Funds' Portfolio Construction Using Machine Learning

The domain of hedge fund investments is undergoing significant transformation, influenced by the rapid expansion of data availability and the advancement of analytical technologies. This study explores the enhancement of hedge fund investment performance through the integration of machine learning techniques, the application of PolyModel feature selection, and the analysis of fund size. We address three critical questions: (1) the effect of machine learning on trading performance, (2) the role of PolyModel feature selection in fund selection and performance, and (3) the comparative reliability of larger versus smaller funds. Our findings offer compelling insights. We observe that while machine learning techniques enhance cumulative returns, they also increase annual volatility, indicating variability in performance. PolyModel feature selection proves to be a robust strategy, with approaches that utilize a comprehensive set of features for fund selection outperforming more selective methodologies. Notably, Long-Term Stability (LTS) effectively manages portfolio volatility while delivering favorable returns. Contrary to popular belief, our results suggest that larger funds do not consistently yield better investment outcomes, challenging the assumption of their inherent reliability. This research highlights the transformative impact of data-driven approaches in the hedge fund investment arena and provides valuable implications for investors and asset managers. By leveraging machine learning and PolyModel feature selection, investors can enhance portfolio optimization and reassess the dependability of larger funds, leading to more informed investment strategies.

q-fin.ST↗

arXiv2024

Reference Signal-Based Waveform Design for Integrated Sensing and Communications System

Integrated sensing and communications (ISAC) as one of the key technologies is capable of supporting high-speed communication and high-precision sensing for the upcoming 6G. This paper studies a waveform strategy by designing the orthogonal frequency division multiplexing (OFDM)-based reference signal (RS) for sensing and communication in ISAC system. We derive the closed-form expressions of Cramér-Rao Bound (CRB) for the distance and velocity estimations, and obtain the communication rate under the mean square error of channel estimation. Then, a weighted sum CRB minimization problem on the distance and velocity estimations is formulated by considering communication rate requirement and RS intervals constraints, which is a mixed-integer problem due to the discrete RS interval values. To solve this problem, some numerical methods are typically adopted to obtain the optimal solutions, whose computational complexity grow exponentially with the number of symbols and subcarriers of OFDM. Therefore, we propose a relaxation and approximation method to transform the original discrete problem into a continuous convex one and obtain the sub-optimal solutions. Finally, our proposed scheme is compared with the exhaustive search method in numerical simulations, which show slight gap between the obtained sub-optimal and optimal solutions, and this gap further decreases with large weight factor.

eess.SP↗

arXiv2024

MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation

Recently, the diffusion-based generative paradigm has achieved impressive general image generation capabilities with text prompts due to its accurate distribution modeling and stable training process. However, generating diverse remote sensing (RS) images that are tremendously different from general images in terms of scale and perspective remains a formidable challenge due to the lack of a comprehensive remote sensing image generation dataset with various modalities, ground sample distances (GSD), and scenes. In this paper, we propose a Multi-modal, Multi-GSD, Multi-scene Remote Sensing (MMM-RS) dataset and benchmark for text-to-image generation in diverse remote sensing scenarios. Specifically, we first collect nine publicly available RS datasets and conduct standardization for all samples. To bridge RS images to textual semantic information, we utilize a large-scale pretrained vision-language model to automatically output text prompts and perform hand-crafted rectification, resulting in information-rich text-image pairs (including multi-modal images). In particular, we design some methods to obtain the images with different GSD and various environments (e.g., low-light, foggy) in a single sample. With extensive manual screening and refining annotations, we ultimately obtain a MMM-RS dataset that comprises approximately 2.1 million text-image pairs. Extensive experimental results verify that our proposed MMM-RS dataset allows off-the-shelf diffusion models to generate diverse RS images across various modalities, scenes, weather conditions, and GSD. The dataset is available at https://github.com/ljl5261/MMM-RS.

eess.IV↗

arXiv2024

Receiver Selection and Transmit Beamforming for Multi-static Integrated Sensing and Communications

Next-generation wireless networks are expected to develop a novel paradigm of integrated sensing and communications (ISAC) to enable both the high-accuracy sensing and high-speed communications. However, conventional mono-static ISAC systems, which simultaneously transmit and receive at the same equipment, may suffer from severe self-interference, and thus significantly degrade the system performance.To address this issue, this paper studies a multi-static ISAC system for cooperative target localization and communications, where the transmitter transmits ISAC signal to multiple receivers (REs) deployed at different positions. We derive the closed-form Cramér-Rao bound (CRB) on the joint estimations of both the transmission delay and Doppler shift for cooperative target localization, and the CRB minimization problem is formulated by considering the cooperative cost and communication rate requirements for the REs. To solve this problem, we first decouple it into two subproblems for RE selection and transmit beamforming, respectively. Then, a minimax linkage-based method is proposed to solve the RE selection subproblem, and a successive convex approximation algorithm is adopted to deal with the transmit beamforming subproblem with non-convex constraints. Finally, numerical results validate our analysis and reveal that our proposed multi-static ISAC scheme achieves better ISAC performance than the conventional mono-static ones when the number of cooperative REs is large.

eess.SP↗

arXiv2024

Quantum spaces associated to mixed polarizations and their limiting behavior on toric varieties

Let $(X, ω, J)$ be a toric variety of dimension $2n$ determined by a Delzant polytope $P$. As indicated in [40], $X$ admits a natural mixed polarization $\mathcal{P}_{k}$, induced by the action of a subtorus $T^{k}$. In this paper, we first establish the quantum space $\mathcal{H}_{k}$ for $\mathcal{P}_{k}$, identifying a basis parameterized by the integer lattice points of $P$. This confirms that the dimension of $\mathcal{H}_{k}$ aligns with those derived from Kähler and real polarizations. Secondly, we examine a one-parameter family of Kähler polarizations $\mathcal{P}_{k,t}$, defined via symplectic potentials, and demonstrate their convergence to $\mathcal{P}_{k}$. Thirdly, we verify that these polarizations $\mathcal{P}_{k,t}$ coincide with those induced by imaginary-time flow. Finally, we explore the relationship between the quantum space $\mathcal{H}_{k,0}$ and $\mathcal{H}_{k}$, establishing that ``$\lim_{t \rightarrow \infty} \mathcal{H}_{k,t} = \mathcal{H}_{k}$."

math.SG↗

arXiv2024

Limit of geometric quantizations on Kähler manifolds with T-symmetry

A compact Kähler manifold $\left( M,ω,J\right) $ with $T$-symmetry admits a natural mixed polarization $\mathcal{P}_{\mathrm{mix}}$ whose real directions come from the $T$-action. In \cite{LW1}, we constructed a one-parameter family of Kähler structures $\left( ω,J_{t}\right) $'s with the same underlying Kä hler form $ω$ and $J_{0}=J$, such that (i) there is a $T$-equivariant biholomorphism between $\left( M,J_{0}\right) $ and $\left( M,J_{t}\right) $ and (ii) Kähler polarizations $\mathcal{P} _{t}$'s corresponding to $J_{t}$'s converge to $\mathcal{P}_{\mathrm{mix}}$ as $t$ goes to infinity. In this paper, we study the quantum analog of above results. Assume $L$ is a pre-quantum line bundle on $\left( M,ω\right) $. Let $\mathcal{H}_{t}$ and $ \mathcal{H}_{\mathrm{mix}}$ be quantum spaces defined using polarizations $\mathcal{P}_{t}$ and $\mathcal{P}_{\mathrm{mix}}$ respectively. In particular, $\mathcal{H}_{t}=H_{\bar{\partial}_{t}}^{0}\left( M,L\right) $. They are both representations of $T$. We show that (i) there is a $T$-equivariant isomorphism between $\mathcal{H}_{0}$ and $\mathcal{H}_{\mathrm{mix}}$ and (ii) for regular $T$-weight $λ$, corresponding $λ$-weight spaces $ \mathcal{H}_{t,λ}$'s converge to $\mathcal{H}_{\mathrm{mix},λ}$ as $t$ goes to infinity.

math.SG↗