Research
Research
Research
Research
4,118+ open-access research outputs.
Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade perform…
The chemical bond is a central organizing concept in chemistry, yet it is absent from the molecular Hamiltonian and no "bond operator" exists. Bonding is therefore not a primitive physical entity but …
The cosmological constant (CC, $\Lambda$) problem represents a remarkable discrepancy of about 120 orders of magnitude between the observed dark energy and its natural expectation from quantum field t…
We study cooperative shortest path planning for an unmanned ground vehicle (UGV) assisted by an unmanned aerial vehicle (UAV) in environments with unknown road blockages that are only discovered when …
The development of intelligent and diversified ser vices in urban rail transit (URT) has resulted in an increasing de mand for high-rate communication between vehicles and ground equipment. However, e…
Vehicle-to-Grid (V2G) technology allows bidirectional power flow for real-time grid support, making electric vehicles (EVs) well-suited for ancillary services such as frequency regulation. However, ex…
Efficient and fair spectrum allocation is a central challenge in 6G networks, where massive connectivity and heterogeneous services continuously compete for limited radio resources. We investigate the…
This paper introduces VDLF-Net, which attaches a compact VAE to a multi-scale CNN backbone. Latent vectors and softmax-gate support the backbone feature maps, while $\ell_2$-normalized embeddings from…
This paper proposes a new method to improve the training efficiency of deep convolutional neural networks. During training, the method evaluates scores to measure how much each layer's parameters chan…
Reconstructing high-fidelity fluid dynamics from sparse temporal observations is quite challenging, mainly due to the chaotic and non-linear nature of fluid transport. Standard deep learning-based int…
Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible relation phrases beyond a fixed predicate set. Existing methods usually treat annotated triplets as positives …
Surface functionalization plays a decisive role in the performance of biosensors, as it governs the efficiency and stability of biomolecule immobilization at the sensor interface and, consequently, th…
Open-vocabulary scene graph generation (SGG) aims to describe visual scenes with flexible and fine-grained relation phrases beyond a fixed predicate vocabulary. While recent vision-language models gre…
Federated learning (FL) aggregation on serverless platforms faces a hard scalability ceiling: existing architectures (lambda-FL, LIFL) partition clients across aggregators, but every aggregator must h…
Feature attribution methods explain the predictions of deep neural networks by assigning importance scores to individual input features. However, most existing methods focus solely on marginal effects…
We study the generalized Lam\'e equation on an elliptic curve $E$ with multiple singularities. By restricting to the locus admitting solutions with quasi-periodic properties, we construct two curves: …
The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in actual visual evidence. However, existing datasets fa…
This paper provides a new class of examples for the Koszul dualities established in~\cite{5}. We study quadratic monomial algebras from the perspective of Koszul duality, with particular emphasis on f…
Clinicians lack a principled framework to quantify diagnostic utility in ultrasound reconstructions. Existing standards like PSNR and VGG-LPIPS are inadequate, failing to account for modality-specific…
Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, determi…
Free open-access publishing with Google Scholar indexing.
Submission Guide →