arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 541 records · Page 30Linked to original sources

arXiv2025

nnMobileNet++: Towards Efficient Hybrid Networks for Retinal Image Analysis

Retinal imaging is a critical, non-invasive modality for the early detection and monitoring of ocular and systemic diseases. Deep learning, particularly convolutional neural networks (CNNs), has significant progress in automated retinal analysis, supporting tasks such as fundus image classification, lesion detection, and vessel segmentation. As a representative lightweight network, nnMobileNet has demonstrated strong performance across multiple retinal benchmarks while remaining computationally efficient. However, purely convolutional architectures inherently struggle to capture long-range dependencies and model the irregular lesions and elongated vascular patterns that characterize on retinal images, despite the critical importance of vascular features for reliable clinical diagnosis. To further advance this line of work and extend the original vision of nnMobileNet, we propose nnMobileNet++, a hybrid architecture that progressively bridges convolutional and transformer representations. The framework integrates three key components: (i) dynamic snake convolution for boundary-aware feature extraction, (ii) stage-specific transformer blocks introduced after the second down-sampling stage for global context modeling, and (iii) retinal image pretraining to improve generalization. Experiments on multiple public retinal datasets for classification, together with ablation studies, demonstrate that nnMobileNet++ achieves state-of-the-art or highly competitive accuracy while maintaining low computational cost, underscoring its potential as a lightweight yet effective framework for retinal image analysis.

cs.CV↗

arXiv2025

FastAnimate: Towards Learnable Template Construction and Pose Deformation for Fast 3D Human Avatar Animation

3D human avatar animation aims at transforming a human avatar from an arbitrary initial pose to a specified target pose using deformation algorithms. Existing approaches typically divide this task into two stages: canonical template construction and target pose deformation. However, current template construction methods demand extensive skeletal rigging and often produce artifacts for specific poses. Moreover, target pose deformation suffers from structural distortions caused by Linear Blend Skinning (LBS), which significantly undermines animation realism. To address these problems, we propose a unified learning-based framework to address both challenges in two phases. For the former phase, to overcome the inefficiencies and artifacts during template construction, we leverage a U-Net architecture that decouples texture and pose information in a feed-forward process, enabling fast generation of a human template. For the latter phase, we propose a data-driven refinement technique that enhances structural integrity. Extensive experiments show that our model delivers consistent performance across diverse poses with an optimal balance between efficiency and quality,surpassing state-of-the-art (SOTA) methods.

cs.CV↗

arXiv2025

Tomographic beta-gamma spectroscopy of nuclear beta decay

Nuclear $β$ decay, a sensitive probe of nuclear structure and weak interactions, has become a precision test bed for physics beyond the Standard Model, driven by recent advances in spectrometric techniques. Here we introduce tomographic $β$-$γ$ spectroscopy (TBGS) of nuclear $β$ decay, a method that detects the energies of $β$, $γ$, and internal conversion electrons while simultaneously reconstructing the energy deposition vertices. Using the PandaX-4T detector operated as a TBGS, we obtain a precise and unbiased decay scheme of $^{214}$Pb, a key background isotope in searches for dark matter and Majorana neutrinos. For the first time, transitions of $^{214}$Pb to both the ground and excited states of $^{214}$Bi are measured concurrently, revealing discrepancies in branching ratios of up to 4.7$σ$ relative to previous evaluations. Combined with state-of-the-art theoretical spectral-shape calculations, these results establish a new benchmark for background modelling in rare-event searches and highlight the potential of TBGS as a versatile tool for fundamental physics and nuclear applications.

nucl-ex↗

arXiv2025

Prompt-OT: An Optimal Transport Regularization Paradigm for Knowledge Preservation in Vision-Language Model Adaptation

Vision-language models (VLMs) such as CLIP demonstrate strong performance but struggle when adapted to downstream tasks. Prompt learning has emerged as an efficient and effective strategy to adapt VLMs while preserving their pre-trained knowledge. However, existing methods still lead to overfitting and degrade zero-shot generalization. To address this challenge, we propose an optimal transport (OT)-guided prompt learning framework that mitigates forgetting by preserving the structural consistency of feature distributions between pre-trained and fine-tuned models. Unlike conventional point-wise constraints, OT naturally captures cross-instance relationships and expands the feasible parameter space for prompt tuning, allowing a better trade-off between adaptation and generalization. Our approach enforces joint constraints on both vision and text representations, ensuring a holistic feature alignment. Extensive experiments on benchmark datasets demonstrate that our simple yet effective method can outperform existing prompt learning strategies in base-to-novel generalization, cross-dataset evaluation, and domain generalization without additional augmentation or ensemble techniques. The code is available at https://github.com/ChongQingNoSubway/Prompt-OT

cs.CV↗

arXiv2025

Enhanced Partially Relevant Video Retrieval through Inter- and Intra-Sample Analysis with Coherence Prediction

Partially Relevant Video Retrieval (PRVR) aims to retrieve the target video that is partially relevant to the text query. The primary challenge in PRVR arises from the semantic asymmetry between textual and visual modalities, as videos often contain substantial content irrelevant to the query. Existing methods coarsely align paired videos and text queries to construct the semantic space, neglecting the critical cross-modal dual nature inherent in this task: inter-sample correlation and intra-sample redundancy. To this end, we propose a novel PRVR framework to systematically exploit these two characteristics. Our framework consists of three core modules. First, the Inter Correlation Enhancement (ICE) module captures inter-sample correlation by identifying semantically similar yet unpaired text queries and video moments, combining them to form pseudo-positive pairs for more robust semantic space construction. Second, the Intra Redundancy Mining (IRM) module mitigates intra-sample redundancy by mining redundant moment features and distinguishing them from query-relevant moments, encouraging the model to learn more discriminative representations. Finally, to reinforce these modules, we introduce the Temporal Coherence Prediction (TCP) module, enhancing discrimination of fine-grained moment-level semantics by training the model to predict the original temporal order of randomly shuffled video sequences. Extensive experiments demonstrate the superiority of our method, achieving state-of-the-art results.

cs.CV↗

arXiv2025

Real-PGDN: A Two-level Classification Method for Full-Process Recognition of Newly Registered Pornographic and Gambling Domain Names

Online pornography and gambling have consistently posed regulatory challenges for governments, threatening both personal assets and privacy. Therefore, it is imperative to research the classification of the newly registered Pornographic and Gambling Domain Names (PGDN). However, scholarly investigation into this topic is limited. Previous efforts in PGDN classification pursue high accuracy using ideal sample data, while others employ up-to-date data from real-world scenarios but achieve lower classification accuracy. This paper introduces the Real-PGDN method, which accomplishes a complete process of timely and comprehensive real-data crawling, feature extraction with feature-missing tolerance, precise PGDN classification, and assessment of application effects in actual scenarios. Our two-level classifier, which integrates CoSENT (BERT-based), Multilayer Perceptron (MLP), and traditional classification algorithms, achieves a 97.88% precision. The research process amasses the NRD2024 dataset, which contains continuous detection information over 20 days for 1,500,000 newly registered domain names across 6 directions. Results from our case study demonstrate that this method also maintains a forecast precision of over 70% for PGDN that are delayed in usage after registration.

cs.CR↗

arXiv2025

A Multi-View Multi-Timescale Hypergraph-Empowered Spatiotemporal Framework for EV Charging Forecasting

Accurate electric vehicle (EV) charging demand forecasting is essential for stable grid operation and proactive EV participation in electricity market. Existing forecasting methods, particularly those based on graph neural networks, are often limited to modeling pairwise relationships between stations, failing to capture the complex, group-wise dynamics inherent in urban charging networks. To address this gap, we develop a novel forecasting framework namely HyperCast, leveraging the expressive power of hypergraphs to model the higher-order spatiotemporal dependencies hidden in EV charging patterns. HyperCast integrates multi-view hypergraphs, which capture both static geographical proximity and dynamic demand-based functional similarities, along with multi-timescale inputs to differentiate between recent trends and weekly periodicities. The framework employs specialized hyper-spatiotemporal blocks and tailored cross-attention mechanisms to effectively fuse information from these diverse sources: views and timescales. Extensive experiments on four public datasets demonstrate that HyperCast significantly outperforms a wide array of state-of-the-art baselines, demonstrating the effectiveness of explicitly modeling collective charging behaviors for more accurate forecasting.

cs.LG↗

arXiv2025

VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction

Reconstructing dynamic 4D scenes is challenging, as it requires robust disentanglement of dynamic objects from the static background. While 3D foundation models like VGGT provide accurate 3D geometry, their performance drops markedly when moving objects dominate. Existing 4D approaches often rely on external priors, heavy post-optimization, or require fine-tuning on 4D datasets. In this paper, we propose VGGT4D, a training-free framework that extends the 3D foundation model VGGT for robust 4D scene reconstruction. Our approach is motivated by the key finding that VGGT's global attention layers already implicitly encode rich, layer-wise dynamic cues. To obtain masks that decouple static and dynamic elements, we mine and amplify global dynamic cues via gram similarity and aggregate them across a temporal window. To further sharpen mask boundaries, we introduce a refinement strategy driven by projection gradient. We then integrate these precise masks into VGGT's early-stage inference, effectively mitigating motion interference in both pose estimation and geometric reconstruction. Across six datasets, our method achieves superior performance in dynamic object segmentation, camera pose estimation, and dense reconstruction. It also supports single-pass inference on sequences longer than 500 frames.

cs.CV↗

arXiv2025

High-pressure melting and elastic behavior of vanadium and niobium based on ab initio and machine learning molecular dynamics

Under high pressure, the group-VB transition metals vanadium (V) and niobium (Nb) exhibit simple crystal structures but complex physical behaviors, such as anomalous compression-induced softening and heating-induced hardening (CISHIH). Meanwhile, the impact of lattice thermal expansion-induced softening at elevated temperatures on HIH is yet to be investigated. Therefore, this study utilized ab initio (AIMD) and machine learning molecular dynamics (MLMD) to investigate the melting and abnormal mechanical softening-hardening behaviors of V and Nb under high pressure. Simulations reveal that the high-temperature Pnma phase of Nb reported in previous experimental studies is highly susceptible to mechanical instability and reverts to the body-centered cubic (BCC) phase. This discovery prompted a revised determination of the high-pressure melting line of Nb. The melting temperature of Nb significantly exceeds the existing theoretical and experimental estimate compared with that of V. AIMD simulations demonstrate that atomic thermal displacements have a greater influence on the HIH of V and Nb than pure electron temperature effects. In addition, the temperature-dependent anomalous elastic properties of V and Nb were investigated within a pressure range of 0-250 GPa using MLMD. The mechanical properties of V and Nb transitioned from HIH to heating-induced softening, elucidating the competition between thermal-expansion-induced softening and HIH. This study advances fundamental understanding of V and Nb physics, providing crucial theoretical foundations for establishing accurate equations of state and constitutive models for these metals.

cond-mat.mtrl-sci↗

arXiv2025

Beyond SELECT: A Comprehensive Taxonomy-Guided Benchmark for Real-World Text-to-SQL Translation

Text-to-SQL datasets are essential for training and evaluating text-to-SQL models, but existing datasets often suffer from limited coverage and fail to capture the diversity of real-world applications. To address this, we propose a novel taxonomy for text-to-SQL classification based on dimensions including core intents, statement types, syntax structures, and key actions. Using this taxonomy, we evaluate widely used public text-to-SQL datasets (e.g., Spider and Bird) and reveal limitations in their coverage and diversity. We then introduce a taxonomy-guided dataset synthesis pipeline, yielding a new dataset named SQL-Synth. This approach combines the taxonomy with Large Language Models (LLMs) to ensure the dataset reflects the breadth and complexity of real-world text-to-SQL applications. Extensive analysis and experimental results validate the effectiveness of our taxonomy, as SQL-Synth exhibits greater diversity and coverage compared to existing benchmarks. Moreover, we uncover that existing LLMs typically fall short in adequately capturing the full range of scenarios, resulting in limited performance on SQL-Synth. However, fine-tuning can substantially improve their performance in these scenarios. The proposed taxonomy has significant potential impact, as it not only enables comprehensive analysis of datasets and the performance of different LLMs, but also guides the construction of training data for LLMs.

cs.CL↗

arXiv2025

VAOT: Vessel-Aware Optimal Transport for Retinal Fundus Enhancement

Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhancement pipelines are typically GAN-based, however, they can distort clinically critical vasculature, altering vessel topology and endpoint integrity. Motivated by these structural alterations, we propose Vessel-Aware Optimal Transport (\textbf{VAOT}), a framework that combines an optimal-transport objective with two structure-preserving regularizers: (i) a skeleton-based loss to maintain global vascular connectivity and (ii) an endpoint-aware loss to stabilize local termini. These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure. Experimental results on synthetic degradation benchmark and downstream evaluations in vessel and lesion segmentation demonstrate the superiority of the proposed methods against several state-of-the art baselines. The code is available at https://github.com/Retinal-Research/VAOT

cs.CV↗

arXiv2025

Large Language Model-Assisted Planning of Electric Vehicle Charging Infrastructure with Real-World Case Study

The growing demand for electric vehicle (EV) charging infrastructure presents significant planning challenges, requiring efficient strategies for investment and operation to deliver cost-effective charging services. However, the potential benefits of EV charging assignment, particularly in response to varying spatial-temporal patterns of charging demand, remain under-explored in infrastructure planning. This paper proposes an integrated approach that jointly optimizes investment decisions and charging assignments while accounting for spatial-temporal demand dynamics and their interdependencies. To support efficient model development, we leverage a large language model (LLM) to assist in generating and refining the mathematical formulation from structured natural-language descriptions, significantly reducing the modeling burden. The resulting optimization model enables optimal joint decision-making for investment and operation. Additionally, we propose a distributed optimization algorithm based on the Alternating Direction Method of Multipliers (ADMM) to address computational complexity in high-dimensional scenarios, which can be executed on standard computing platforms. We validate our approach through a case study using 1.5 million real-world travel records from Chengdu, China, demonstrating a 30% reduction in total cost compared to a baseline without EV assignment.

eess.SY↗

arXiv2025

Appraising the absolute limits of nanotubes and nanospheres to preserve high-pressure materials

Matter under high pressure often exhibits attractive properties, which, unfortunately, are typically irretrievable when released to ambient conditions. Intuitively, nanostructure engineering might provide a promising route to contain high-pressure phase of materials because of the exceptional mechanical strength at nanoscale. However, there is no available theoretical model that can analyze this possibility, not to mention to quantitatively evaluate the pressure-bearing capability of nano-cavities. Here, a physical model is proposed to appraise the absolute theoretical limit of various nanotubes/nanospheres to preserve high-pressure materials to ambient conditions. By incorporating with first-principles calculations, we screen and select four types of representative nanomaterials: graphene, hexagonal boron nitride (h-BN), biphenylene, and γ-graphyne, and perform systematic investigations. The results indicate that nanotube/nanosphere of graphene exhibits the best pressure-bearing capability, followed by h-BN, biphenylene and γ-graphyne. Our model reveals that the structure with the largest average binding energy per bond and the highest density of bonds will have the highest absolute limit to contain pressure materials, while electron/hole doping and interlayer interactions have minor effects. Our finding suggests that one can utilize nanotube/nanosphere with multiple layers to retrieve compressed material with higher pressures. For example, a single layer graphene sphere can retrieve compressed LaH10 with a volume size of 26 nm3 that corresponding to a pressure of 170 GPa and with a near room temperature superconductor transition of Tc=250 K. Similarly, in order to retrieve the metastable atomic hydrogen or molecular metallic hydrogen at about 250 GPa, it requires only three layers of a nanosphere to contain a volume size of 173 nm^3.

cond-mat.mtrl-sci↗

arXiv2025

Hyperbolic Dispersion and Low-Frequency Plasmons in Electrides

Natural hyperbolic materials have attracted significant interest in the field of photonics due to their unique optical properties. Based on the initial successful explorations on layered crystalline materials, hyperbolic dispersion was associated with extreme structural anisotropy, despite the rarity of natural materials exhibiting this property. Here we show that non cubic electrides are generally promising natural hyperbolic materials owing to charge localization in interstitial sites. This includes elemental and binary electrides, as well as some two-dimensional materials that show prominent in-plane hyperbolic dispersion. They exhibit low plasma frequencies and a broad hyperbolic window spanning the infrared to the ultraviolet. In semiconductor electrides, anisotropic interband transitions provide an additional mechanism for hyperbolic behaviour. These findings remove the previously held prerequisite of structural anisotropy for natural hyperbolic materials, and open up new opportunities, which might change the current strategy for searching and design photonic materials.

physics.optics↗

arXiv2025

Ferroelectricity-driven altermagnetism in two-dimensional van der Waals multiferroics

Altermagnets (AMs) are a recently identified class of unconventional collinear compensated antiferromagnets that exhibit momentum-dependent spin splitting despite having zero net magnetization. This unconventional magnetic order gives rise to a range of phenomena, including the anomalous Hall effect, chiral magnons, and nonlinear photocurrents. Here, using spin space group (SSG) symmetry analysis and first-principles calculations, we demonstrate an efficient strategy to control altermagnetism in two-dimensional multiferroics through ferroelectric polarization and interlayer sliding. For material realization, we find that monolayer and bilayer FeCuP2S6 exhibit finite spin splitting when ferroelectric sublattices are connected by nonsymmorphic screw-axis operations rather than pure translation or inversion symmetry. Interlayer sliding further enables reversible switching or suppression of spin splitting through modifications of the SSG. Our calculations further reveal that the anomalous Hall response serves as a direct probe of these spin-split states. These findings establish two-dimensional van der Waals multiferroics as promising platforms for realizing electrically controllable altermagnetism and advancing next-generation spintronic and magnetoelectric technologies.

cond-mat.mtrl-sci↗

arXiv2025

Dark energy after pre-recombination early dark energy in light of DESI DR2 and the latest ACT and SPT data

It has been noted that with the pre-recombination early dark energy (EDE) resolution of Hubble tension, the preference of recent datasets for the evolving dark energy (DE) can be suppressed significantly. In this work, we clarify and reconfirm this result with DESI DR2 and the latest ACT DR6 and SPT-3G D1, the tightest small-scale CMB constraints up to date. In the $w_0w_a$CDM model with EDE, a quintessence-like component ($w_0+w_a\geq-1$) can be 1$σ$ consistent with Planck+ACT+SPT+DESI+Pantheon+SH0ES datasets, and $Δχ^2\lesssim -14$ compared with $w_0w_a$CDM model without EDE. This reveals the possibility that when the potential resolutions of Hubble tension are considered, current accelerated expansion can attribute to a canonical evolving scalar field or cosmological constant, and again highlights the importance of re-examining the nature of DE within the broader context of cosmological tensions.

astro-ph.CO↗

arXiv2025

DDTime: Dataset Distillation with Spectral Alignment and Information Bottleneck for Time-Series Forecasting

Time-series forecasting is fundamental across many domains, yet training accurate models often requires large-scale datasets and substantial computational resources. Dataset distillation offers a promising alternative by synthesizing compact datasets that preserve the learning behavior of full data. However, extending dataset distillation to time-series forecasting is non-trivial due to two fundamental challenges: 1.temporal bias from strong autocorrelation, which leads to distorted value-term alignment between teacher and student models; and 2.insufficient diversity among synthetic samples, arising from the absence of explicit categorical priors to regularize trajectory variety. In this work, we propose DDTime, a lightweight and plug-in distillation framework built upon first-order condensation decomposition. To tackle Challenge 1, it revisits value-term alignment through temporal statistics and introduces a frequency-domain alignment mechanism to mitigate autocorrelation-induced bias, ensuring spectral consistency and temporal fidelity. To address Challenge 2, we further design an inter-sample regularization inspired by the information bottleneck principle, which enhances diversity and maximizes information density across synthetic trajectories. The combined objective is theoretically compatible with a wide range of condensation paradigms and supports stable first-order optimization. Extensive experiments on 20 benchmark datasets and diverse forecasting architectures demonstrate that DDTime consistently outperforms existing distillation methods, achieving about 30% relative accuracy gains while introducing about 2.49% computational overhead. All code and distilled datasets will be released.

cs.LG↗

arXiv2025

MicroEvoEval: A Systematic Evaluation Framework for Image-Based Microstructure Evolution Prediction

Simulating microstructure evolution (MicroEvo) is vital for materials design but demands high numerical accuracy, efficiency, and physical fidelity. Although recent studies on deep learning (DL) offer a promising alternative to traditional solvers, the field lacks standardized benchmarks. Existing studies are flawed due to a lack of comparing specialized MicroEvo DL models with state-of-the-art spatio-temporal architectures, an overemphasis on numerical accuracy over physical fidelity, and a failure to analyze error propagation over time. To address these gaps, we introduce MicroEvoEval, the first comprehensive benchmark for image-based microstructure evolution prediction. We evaluate 14 models, encompassing both domain-specific and general-purpose architectures, across four representative MicroEvo tasks with datasets specifically structured for both short- and long-term assessment. Our multi-faceted evaluation framework goes beyond numerical accuracy and computational cost, incorporating a curated set of structure-preserving metrics to assess physical fidelity. Our extensive evaluations yield several key insights. Notably, we find that modern architectures (e.g., VMamba), not only achieve superior long-term stability and physical fidelity but also operate with an order-of-magnitude greater computational efficiency. The results highlight the necessity of holistic evaluation and identify these modern architectures as a highly promising direction for developing efficient and reliable surrogate models in data-driven materials science.

cond-mat.mtrl-sci↗