SearcharxivSearch

arXiv subjects

Yuxin Xu

Publications and source records attributed to Yuxin Xu.

3 recordsLinked to original sources

Complex VAE with Heavy-Tailed Likelihood for Radar Target Detection in Sea Clutter

To address the heavy-tailed, spike-prone nature of sea clutter and the scarcity of labeled target data, an unsupervised complex-valued variational autoencoder (VAE) for maritime radar target detection is proposed. In implementation, each complex baseband slow-time sequence is represented by its in-phase and quadrature components, and the model learns their joint reconstruction from clutter-only data. A Student-\(t\) negative log-likelihood is adopted to capture heavy-tailed reconstruction errors while reducing sensitivity to outliers during clutter learning. In addition, a time-domain amplitude error constraint is introduced to penalize slow-time magnitude mismatch in the reconstruction. At inference, reconstruction deviation is used as the detection statistic, and the decision threshold is set via an empirical quantile estimated from a clutter-only validation set to enforce a constant false-alarm rate (CFAR). Experiments on measured sea-clutter data show that detection performance is consistently improved over MF, AMF, and a real-valued \(β\)-VAE under CFAR constraints.

eess.SP

EquiFlow: Equivariant Conditional Flow Matching with Optimal Transport for 3D Molecular Conformation Prediction

Molecular 3D conformations play a key role in determining how molecules interact with other molecules or protein surfaces. Recent deep learning advancements have improved conformation prediction, but slow training speeds and difficulties in utilizing high-degree features limit performance. We propose EquiFlow, an equivariant conditional flow matching model with optimal transport. EquiFlow uniquely applies conditional flow matching in molecular 3D conformation prediction, leveraging simulation-free training to address slow training speeds. It uses a modified Equiformer model to encode Cartesian molecular conformations along with their atomic and bond properties into higher-degree embeddings. Additionally, EquiFlow employs an ODE solver, providing faster inference speeds compared to diffusion models with SDEs. Experiments on the QM9 dataset show that EquiFlow predicts small molecule conformations more accurately than current state-of-the-art models.

cs.LG

Echo chamber effects based on a novel three-dimensional Deffuant-Weisbuch model

In order to solve the problem of opinion polarization and distortion caused by echo chamber effect in the evolution process of online public opinion,a three-dimensional Deffuant-Weisbuch model is proposed to study the formation and elimination of echo chamber effect in this paper. Firstly, the original pairwise interaction model is generalized to three-point interaction model. Secondly, we consider individual psychological mechanism and introduce individual emotional factor into the trust threshold of original model. Finally, the natural evolution coefficient of opinion is introduced to modify the model. The improved model is used to conduct simulation experiments on social networks with different structures, and opinion leaders and active agents are introduced into the network, so as to study the corresponding generation and breaking mechanism of echo chamber. The experimental results show that the change of network structure cannot eliminate the echo chamber effect, and the increase of network stability and connectivity can only slow down the echo chamber effect. Opinion leaders can aggregate opinions within their scope of influence and have a guiding effect on opinions. Therefore, if opinion leaders can change their opinions over time, they can well guide opinions to converge to neutral opinions, thus achieving the purpose of breaking the echo chamber. Active agents can lead the opinions in the network to converge to the neutral, and active agents with high stubbornness can lead the free views to converge to the neutral, thus achieving the purpose of breaking the echo chamber effect.

physics.soc-ph