arXiv subjects

Ling Wang

Publications and source records attributed to Ling Wang.

At least 55 records · Page 3Linked to original sources

arXiv2025

Vehicle-group-based Crash Risk Prediction and Interpretation on Highways

Previous studies in predicting crash risks primarily associated the number or likelihood of crashes on a road segment with traffic parameters or geometric characteristics, usually neglecting the impact of vehicles' continuous movement and interactions with nearby vehicles. Recent technology advances, such as Connected and Automated Vehicles (CAVs) and Unmanned Aerial Vehicles (UAVs) are able to collect high-resolution trajectory data, which enables trajectory-based risk analysis. This study investigates a new vehicle group (VG) based risk analysis method and explores risk evolution mechanisms considering VG features. An impact-based vehicle grouping method is proposed to cluster vehicles into VGs by evaluating their responses to the erratic behaviors of nearby vehicles. The risk of a VG is aggregated based on the risk between each vehicle pair in the VG, measured by inverse Time-to-Collision (iTTC). A Logistic Regression and a Graph Neural Network (GNN) are then employed to predict VG risks using aggregated and disaggregated VG information. Both methods achieve excellent performance with AUC values exceeding 0.93. For the GNN model, GNNExplainer with feature perturbation is applied to identify critical individual vehicle features and their directional impact on VG risks. Overall, this research contributes a new perspective for identifying, predicting, and interpreting traffic risks.

cs.LG↗

arXiv2025

PDCNet: a benchmark and general deep learning framework for activity prediction of peptide-drug conjugates

Peptide-drug conjugates (PDCs) represent a promising therapeutic avenue for human diseases, particularly in cancer treatment. Systematic elucidation of structure-activity relationships (SARs) and accurate prediction of the activity of PDCs are critical for the rational design and optimization of these conjugates. To this end, we carefully design and construct a benchmark PDCs dataset compiled from literature-derived collections and PDCdb database, and then develop PDCNet, the first unified deep learning framework for forecasting the activity of PDCs. The architecture systematically captures the complex factors underlying anticancer decisions of PDCs in real-word scenarios through a multi-level feature fusion framework that collaboratively characterizes and learns the features of peptides, linkers, and payloads. Leveraging a curated PDCs benchmark dataset, comprehensive evaluation results show that PDCNet demonstrates superior predictive capability, with the highest AUC, F1, MCC and BA scores of 0.9213, 0.7656, 0.7071 and 0.8388 for the test set, outperforming eight established traditional machine learning models. Multi-level validations, including 5-fold cross-validation, threshold testing, ablation studies, model interpretability analysis and external independent testing, further confirm the superiority, robustness, and usability of the PDCNet architecture. We anticipate that PDCNet represents a novel paradigm, incorporating both a benchmark dataset and advanced models, which can accelerate the design and discovery of new PDC-based therapeutic agents.

cs.LG↗

arXiv2025

Neighborhood Overlap-Aware High-Order Graph Neural Network for Dynamic Graph Learning

Dynamic graph learning (DGL) aims to learn informative and temporally-evolving node embeddings to support downstream tasks such as link prediction. A fundamental challenge in DGL lies in effectively modeling both the temporal dynamics and structural dependencies of evolving graph topologies. Recent advances in Dynamic Graph Neural Networks (DGNNs) have obtained remarkable success by leveraging message-passing mechanisms to capture pairwise node interactions. However, these approaches often overlook more complex structural patterns, particularly neighborhood overlap, which can play a critical role in characterizing node interactions. To overcome this limitation, we introduce the Neighborhood Overlap-Aware High-Order Graph Neural Network (NO-HGNN), which is built upon two key innovations: (a) computing a correlation score based on the extent of neighborhood overlap to better capture complex node interactions; and (b) embedding this correlation directly into the message-passing process of high-order graph neural networks in the DGL. Experiments on two real-world dynamic graphs show that NO-HGNN achieves notable improvements in link prediction accuracy, outperforming several state-of-the-art approaches.

cs.SI↗

arXiv2025

High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction

Link prediction is a fundamental task in dynamic graph learning (DGL), inherently shaped by the topology of the DG. Recent advancements in dynamic graph neural networks (DGNN), primarily by modeling the relationships among nodes via a message passing scheme, have significantly improved link prediction performance. However, DGNNs heavily rely on the pairwise node interactions, which neglect the common neighbor interaction in DGL. To address this limitation, we propose a High-order Graph Neural Networks with Common Neighbor Awareness (HGNN-CNA) for link prediction with two-fold ideas: a) estimating correlation score by considering multi-hop common neighbors for capturing the complex interaction between nodes; b) fusing the correlation into the message-passing process to consider common neighbor interaction directly in DGL. Experimental results on three real DGs demonstrate that the proposed HGNN-CNA acquires a significant accuracy gain over several state-of-the-art models on the link prediction task.

cs.LG↗

arXiv2025

Ground state phase diagram and the exotic phases in the spin-1/2 square lattice J1-J2-Jx model

The intricate interplay between frustration and spin chirality has the potential to give rise to unprecedented phases in frustrated quantum magnets. We examine the ground state phase diagram of the spin-1/2 square lattice J1-J2-Jx model by employing critical level crossings and ground state fidelity susceptibility (FS) using exact diagonalization (ED) with full lattice symmetries. Our analysis reveals the evolution of highly symmetric energy levels as a function of J2 at fixed Jx. During a magnetic to non-magnetic phase transition, the precise identification of the phase boundary is achieved through critical level crossings between the gapless excitation of a magnetic phase and the quasi-degenerate ground state of a non-magnet phase. Conversely, a direct transition between two non-magnetic phases is characterized by a FS peak accompanied by an avoided ground state level crossing, serving as a distinctive signal. Within a substantial range of Jx, we identify an anticipated chiral spin liquid (CSL) state and an adjacent nematic spin liquid (NSL) phase with a degeneracy of two on a cylinder. These two phases are demarcated by a nearly vertical boundary line at J2 = 0.65. This critical line terminates at the lower boundary of a magnetic ordered chiral spin solid (CSS) phase. We validate the topological nature of the CSL using the modular S matrix of the minimum entangled states (MES) on a torus, along with the entanglement spectra (ES) of even and odd sectors on a cylinder, employing an SU(2)-symmetric density matrix renormalization group (DMRG) method. Furthermore, we delve into a comprehensive discussion on the nature of the NSL, exploring aspects such as ground state degeneracy, the local bond energy landscape, and the singlet and triplet gaps on various tori. These analysis provide substantial evidence supporting the nematic nature of the NSL.

cond-mat.str-el↗

arXiv2025

Learning eigenstates of quantum many-body Hamiltonians within the symmetric subspaces using neural network quantum states

The exploration of neural network quantum states has become widespread in the studies of complicated quantum many-body systems. However, achieving high precision remains challenging due to the exponential growth of Hilbert space size and the intricate sign structures. Utilizing symmetries of the physical system, we propose a method to evaluate and sample the variational ansatz within a symmetric subspace. This approach isolates different symmetry sectors, reducing the relevant Hilbert space size by a factor approximately proportional to the size of the symmetry group. It is inspired by exact diagonalization techniques and the work of Choo et al. in Phys. Rev. Lett. 121, 167204 (2018). We validate our method using the frustrated spin-1/2 $J_1$-$J_2$ antiferromagnetic Heisenberg chain and compare its performance to the case without symmetrization. The results indicate that our symmetric subspace approach achieves a substantial improvement over the full Hilbert space on optimizing the ansatz, reducing the energy error by orders of magnitude. We also compare the results on degenerate eigenstates with different quantum numbers, highlighting the advantage of operating within a smaller Hilbert subspace.

cond-mat.str-el↗

arXiv2025

Long-range dependent mortality modeling with cointegration

Empirical studies with publicly available life tables identify long-range dependence (LRD) in national mortality data. Although the longevity market is supposed to benchmark against the national force of mortality, insurers are more concerned about the forces of mortality associated with their own portfolios than the national ones. Recent advances on mortality modeling make use of fractional Brownian motion (fBm) to capture LRD. A theoretically flexible approach even considers mixed fBm (mfBm). Using Volterra processes, we prove that the direct use of mfBm encounters the identification problem so that insurers hardly detect the LRD effect from their portfolios. Cointegration techniques can effectively bring the LRD information within the national force of mortality to the mortality models for insurers' experienced portfolios. Under the open-loop equilibrium control framework, the explicit and unique equilibrium longevity hedging strategy is derived for cointegrated forces of mortality with LRD. Using the derived hedging strategy, our numerical examples show that the accuracy of estimating cointegration is crucial for hedging against the longevity exposure of insurers with LRD national force of mortality.

q-fin.RM↗

arXiv2025

Domain-invariant Clinical Representation Learning by Bridging Data Distribution Shift across EMR Datasets

Emerging diseases present challenges in symptom recognition and timely clinical intervention due to limited available information. An effective prognostic model could assist physicians in making accurate diagnoses and designing personalized treatment plans to prevent adverse outcomes. However, in the early stages of disease emergence, several factors hamper model development: limited data collection, insufficient clinical experience, and privacy and ethical concerns restrict data availability and complicate accurate label assignment. Furthermore, Electronic Medical Record (EMR) data from different diseases or sources often exhibit significant cross-dataset feature misalignment, severely impacting the effectiveness of deep learning models. We present a domain-invariant representation learning method that constructs a transition model between source and target datasets. By constraining the distribution shift of features generated across different domains, we capture domain-invariant features specifically relevant to downstream tasks, developing a unified domain-invariant encoder that achieves better feature representation across various task domains. Experimental results across multiple target tasks demonstrate that our proposed model surpasses competing baseline methods and achieves faster training convergence, particularly when working with limited data. Extensive experiments validate our method's effectiveness in providing more accurate predictions for emerging pandemics and other diseases. Code is publicly available at https://github.com/wang1yuhang/domain_invariant_network.

cs.LG↗

arXiv2025

Reinforcement learning Based Automated Design of Differential Evolution Algorithm for Black-box Optimization

Differential evolution (DE) algorithm is recognized as one of the most effective evolutionary algorithms, demonstrating remarkable efficacy in black-box optimization due to its derivative-free nature. Numerous enhancements to the fundamental DE have been proposed, incorporating innovative mutation strategies and sophisticated parameter tuning techniques to improve performance. However, no single variant has proven universally superior across all problems. To address this challenge, we introduce a novel framework that employs reinforcement learning (RL) to automatically design DE for black-box optimization through meta-learning. RL acts as an advanced meta-optimizer, generating a customized DE configuration that includes an optimal initialization strategy, update rule, and hyperparameters tailored to a specific black-box optimization problem. This process is informed by a detailed analysis of the problem characteristics. In this proof-of-concept study, we utilize a double deep Q-network for implementation, considering a subset of 40 possible strategy combinations and parameter optimizations simultaneously. The framework's performance is evaluated against black-box optimization benchmarks and compared with state-of-the-art algorithms. The experimental results highlight the promising potential of our proposed framework.

cs.NE↗

arXiv2024

Flat level sets of Allen-Cahn equation in half-space

We prove a half-space Bernstein theorem for Allen-Cahn equation. More precisely, we show that every solution $u$ of the Allen-Cahn equation in the half-space $\overline{\mathbb{R}^n_+}:=\{(x_1,x_2,\cdots,x_n)\in\mathbb{R}^n:\,x_1\geq 0\}$ with $|u|\leq 1$, boundary value given by the restriction of a one-dimensional solution on $\{x_1=0\}$ and monotone condition $\partial_{x_n}u>0$ as well as limiting condition $\lim_{x_n\to\pm\infty}u(x',x_n)=\pm 1$ must itself be one-dimensional, and the parallel flat level sets and $\{x_1=0\}$ intersect at the same fixed angle in $(0, \fracπ{2}]$.

math.AP↗

arXiv2024

Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions

Recent advancements in deep learning have significantly revolutionized the field of clinical diagnosis and treatment, offering novel approaches to improve diagnostic precision and treatment efficacy across diverse clinical domains, thus driving the pursuit of precision medicine. The growing availability of multi-organ and multimodal datasets has accelerated the development of large-scale Medical Multimodal Foundation Models (MMFMs). These models, known for their strong generalization capabilities and rich representational power, are increasingly being adapted to address a wide range of clinical tasks, from early diagnosis to personalized treatment strategies. This review offers a comprehensive analysis of recent developments in MMFMs, focusing on three key aspects: datasets, model architectures, and clinical applications. We also explore the challenges and opportunities in optimizing multimodal representations and discuss how these advancements are shaping the future of healthcare by enabling improved patient outcomes and more efficient clinical workflows.

cs.AI↗

arXiv2024

Dropout the High-rate Downsampling: A Novel Design Paradigm for UHD Image Restoration

With the popularization of high-end mobile devices, Ultra-high-definition (UHD) images have become ubiquitous in our lives. The restoration of UHD images is a highly challenging problem due to the exaggerated pixel count, which often leads to memory overflow during processing. Existing methods either downsample UHD images at a high rate before processing or split them into multiple patches for separate processing. However, high-rate downsampling leads to significant information loss, while patch-based approaches inevitably introduce boundary artifacts. In this paper, we propose a novel design paradigm to solve the UHD image restoration problem, called D2Net. D2Net enables direct full-resolution inference on UHD images without the need for high-rate downsampling or dividing the images into several patches. Specifically, we ingeniously utilize the characteristics of the frequency domain to establish long-range dependencies of features. Taking into account the richer local patterns in UHD images, we also design a multi-scale convolutional group to capture local features. Additionally, during the decoding stage, we dynamically incorporate features from the encoding stage to reduce the flow of irrelevant information. Extensive experiments on three UHD image restoration tasks, including low-light image enhancement, image dehazing, and image deblurring, show that our model achieves better quantitative and qualitative results than state-of-the-art methods.

cs.CV↗

arXiv2024

Bose-Einstein condensation of a two-magnon bound state in a spin-one triangular lattice

In ordered magnets, the elementary excitations are spin waves (magnons), which obey Bose-Einstein statistics. Similarly to Cooper pairs in superconductors, magnons can be paired into bound states under attractive interactions. The Zeeman coupling to a magnetic field is able to tune the particle density through a quantum critical point (QCP), beyond which a "hidden order" is predicted to exist. Here we report direct observation of the Bose-Einstein condensation (BEC) of the two-magnon bound state in Na$_2$BaNi(PO$_4$)$_2$. Comprehensive thermodynamic measurements confirmed the two-dimensional BEC-QCP at the saturation field. Inelastic neutron scattering experiments were performed to establish the microscopic model. An exact solution revealed stable 2-magnon bound states that were further confirmed by electron spin resonance and nuclear magnetic resonance experiments, demonstrating that the QCP is due to the pair condensation and the phase below saturation field is likely the long-sought-after spin nematic phase.

cond-mat.str-el↗

arXiv2024

BrainDreamer: Reasoning-Coherent and Controllable Image Generation from EEG Brain Signals via Language Guidance

Can we directly visualize what we imagine in our brain together with what we describe? The inherent nature of human perception reveals that, when we think, our body can combine language description and build a vivid picture in our brain. Intuitively, generative models should also hold such versatility. In this paper, we introduce BrainDreamer, a novel end-to-end language-guided generative framework that can mimic human reasoning and generate high-quality images from electroencephalogram (EEG) brain signals. Our method is superior in its capacity to eliminate the noise introduced by non-invasive EEG data acquisition and meanwhile achieve a more precise mapping between the EEG and image modality, thus leading to significantly better-generated images. Specifically, BrainDreamer consists of two key learning stages: 1) modality alignment and 2) image generation. In the alignment stage, we propose a novel mask-based triple contrastive learning strategy to effectively align EEG, text, and image embeddings to learn a unified representation. In the generation stage, we inject the EEG embeddings into the pre-trained Stable Diffusion model by designing a learnable EEG adapter to generate high-quality reasoning-coherent images. Moreover, BrainDreamer can accept textual descriptions (e.g., color, position, etc.) to achieve controllable image generation. Extensive experiments show that our method significantly outperforms prior arts in terms of generating quality and quantitative performance.

cs.CV↗

arXiv2024

DAP-LED: Learning Degradation-Aware Priors with CLIP for Joint Low-light Enhancement and Deblurring

Autonomous vehicles and robots often struggle with reliable visual perception at night due to the low illumination and motion blur caused by the long exposure time of RGB cameras. Existing methods address this challenge by sequentially connecting the off-the-shelf pretrained low-light enhancement and deblurring models. Unfortunately, these methods often lead to noticeable artifacts (\eg, color distortions) in the over-exposed regions or make it hardly possible to learn the motion cues of the dark regions. In this paper, we interestingly find vision-language models, \eg, Contrastive Language-Image Pretraining (CLIP), can comprehensively perceive diverse degradation levels at night. In light of this, we propose a novel transformer-based joint learning framework, named DAP-LED, which can jointly achieve low-light enhancement and deblurring, benefiting downstream tasks, such as depth estimation, segmentation, and detection in the dark. The key insight is to leverage CLIP to adaptively learn the degradation levels from images at night. This subtly enables learning rich semantic information and visual representation for optimization of the joint tasks. To achieve this, we first introduce a CLIP-guided cross-fusion module to obtain multi-scale patch-wise degradation heatmaps from the image embeddings. Then, the heatmaps are fused via the designed CLIP-enhanced transformer blocks to retain useful degradation information for effective model optimization. Experimental results show that, compared to existing methods, our DAP-LED achieves state-of-the-art performance in the dark. Meanwhile, the enhanced results are demonstrated to be effective for three downstream tasks. For demo and more results, please check the project page: \url{https://vlislab22.github.io/dap-led/}.

cs.CV↗

arXiv2024

Vision-Language Meets the Skeleton: Progressively Distillation with Cross-Modal Knowledge for 3D Action Representation Learning

Skeleton-based action representation learning aims to interpret and understand human behaviors by encoding the skeleton sequences, which can be categorized into two primary training paradigms: supervised learning and self-supervised learning. However, the former one-hot classification requires labor-intensive predefined action categories annotations, while the latter involves skeleton transformations (e.g., cropping) in the pretext tasks that may impair the skeleton structure. To address these challenges, we introduce a novel skeleton-based training framework (C$^2$VL) based on Cross-modal Contrastive learning that uses the progressive distillation to learn task-agnostic human skeleton action representation from the Vision-Language knowledge prompts. Specifically, we establish the vision-language action concept space through vision-language knowledge prompts generated by pre-trained large multimodal models (LMMs), which enrich the fine-grained details that the skeleton action space lacks. Moreover, we propose the intra-modal self-similarity and inter-modal cross-consistency softened targets in the cross-modal representation learning process to progressively control and guide the degree of pulling vision-language knowledge prompts and corresponding skeletons closer. These soft instance discrimination and self-knowledge distillation strategies contribute to the learning of better skeleton-based action representations from the noisy skeleton-vision-language pairs. During the inference phase, our method requires only the skeleton data as the input for action recognition and no longer for vision-language prompts. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120, and PKU-MMD datasets demonstrate that our method outperforms the previous methods and achieves state-of-the-art results. Code is available at: https://github.com/cseeyangchen/C2VL.

cs.CV↗

arXiv2024

Singular Abreu equations and linearized Monge-Ampère equations with drifts

We study the solvability of singular Abreu equations which arise in the approximation of convex functionals subject to a convexity constraint. Previous works established the solvability of their second boundary value problems either in two dimensions, or in higher dimensions under either a smallness condition or a radial symmetry condition. Here, we solve the higher dimensional case by transforming singular Abreu equations into linearized Monge-Ampère equations with drifts. We establish global Hölder estimates for the linearized Monge-Ampère equation with drifts under suitable hypotheses, and then use them to the regularity and solvability of the second boundary value problem for singular Abreu equations in higher dimensions. Many cases with general right-hand side will also be discussed.

math.AP↗

arXiv2024

Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning

Dynamic graphs (DG) are often used to describe evolving interactions between nodes in real-world applications. Temporal patterns are a natural feature of DGs and are also key to representation learning. However, existing dynamic GCN models are mostly composed of static GCNs and sequence modules, which results in the separation of spatiotemporal information and cannot effectively capture complex temporal patterns in DGs. To address this problem, this study proposes a spatial-temporal graph convolutional networks with diversified transformation (STGCNDT), which includes three aspects: a) constructing a unified graph tensor convolutional network (GTCN) using tensor M-products without the need to represent spatiotemporal information separately; b) introducing three transformation schemes in GTCN to model complex temporal patterns to aggregate temporal information; and c) constructing an ensemble of diversified transformation schemes to obtain higher representation capabilities. Empirical studies on four DGs that appear in communication networks show that the proposed STGCNDT significantly outperforms state-of-the-art models in solving link weight estimation tasks due to the diversified transformations.

cs.LG↗