arXiv subjects

Su Chen

Publications and source records attributed to Su Chen.

16 recordsLinked to original sources

arXiv2026

Discovering Latent Response Laws in Forced Physical Systems

Governing equations provide compact descriptions of physical systems, yet the variables in which they are simple are often hidden in high-dimensional measurements. This challenge is sharper for forced systems, whose responses depend on both intrinsic dynamics and time-dependent inputs. Here we introduce FLARE, a forced latent autoencoder for response equations that learns compact response coordinates, identifies sparse input-dependent latent dynamics and decodes equation rollouts to full responses. By estimating latent dimension from data and separating state estimation from external forcing, FLARE enables forecasts to be initialized from past responses and driven by prescribed future inputs. Across known dynamical systems, application-scale forced responses and visual observations, FLARE recovers compact forced dynamics and predicts long-horizon high-dimensional responses under inputs not used for training. By turning learned coordinates into a dynamical interface, FLARE extends equation discovery to systems whose effective states are hidden within complex observations, providing a route for interpretable modelling and prediction of high-dimensional responses in forced dynamical systems.

cs.LG↗

arXiv2026

Scenario-conditioned flow matching for probabilistic generation of three-component ground-motion waveforms

Performance-based seismic risk assessment requires three-component acceleration histories compatible with specified source, path, and site conditions. Conventional ground-motion prediction equations provide scalar intensity measures, while many generative waveform models learn amplitude and waveform shape within a single high-dimensional target. We present WaveFlowGMM, a two-stage probabilistic ground-motion model that uses peak ground acceleration (PGA) as an amplitude interface between scenario conditioning and waveform generation. The amplitude stage uses physics-informed symbolic learning to estimate component-wise PGA medians and a full cross-component covariance. The waveform stage uses few-step AlphaFlow in an invertible wavelet-packet coefficient space to generate normalised three-component histories that are rescaled by sampled PGA. Tests on an event-level NGA-West2 holdout set show that the generated motions recover the main magnitude, distance, and site scaling, keep peak and spectral residuals close to zero, preserve three-component amplitude dependence, and yield velocity and displacement histories without systematic drift after integration of the generated three-component acceleration histories. The framework provides an interpretable and computationally efficient candidate component for waveform-level seismic hazard and risk analysis.

physics.geo-ph↗

arXiv2026

EPIC: A System Framework for Efficient Egocentric Perception on Embodied AR Glasses

Modern smart AR glasses are evolving into intelligent systems that support foundation model-based assistance through continuous perception of the user and surrounding environment. However, this perception-first design creates major bottlenecks. Continuously capturing, processing, and storing rich perceptual streams, especially high-resolution egocentric video, imposes substantial power and memory overhead, which is difficult to sustain on resource-constrained AR glasses. In this work, we propose EPIC, an efficient egocentric perception system for embodied intelligence on smart AR glasses. EPIC is an algorithm-hardware co-optimization framework that leverages gaze, pose, and inertial signals to infer user intent and retain only the most informative parts of high-resolution perceptual input, greatly reducing perception overhead. Our results show that EPIC reduces memory footprint by $27.5\times$ and energy consumption by $24.3\times$ on average compared with full video baseline solution, while preserving intelligent assistance accuracy on egocentric video understanding tasks, a key application scenario for embodied intelligence on smart glasses.

cs.AR↗

arXiv2026

Wavelet Packet-Based Diffusion Model for Ground Motion Generation with Multi-Conditional Energy and Spectral Matching

Temporal energy distribution strongly affects nonlinear structural response and cumulative damage. We propose a multi-conditional diffusion framework for ground motion synthesis that simultaneously matches temporal energy evolution and target response spectra. Wavelet packet decomposition provides the signal representation and enables direct waveform reconstruction via orthogonal filter banks. A Transformer-based conditional encoder with cross-attention integrates heterogeneous conditions, including spectral ordinates, Arias intensity, temporal parameters, and Husid curves. The framework adopts the Elucidating Diffusion Model (EDM) with second-order Heun sampling to improve inference efficiency without sacrificing quality. Tests on the NGA-West2 database show that explicit temporal-energy constraints markedly improve control of energy onset and significant duration while preserving spectrum matching and maintaining stable diversity sampling. The framework yields spectrum-compatible motions with realistic energy evolution and supports uncertainty quantification via conditional diversity sampling.

physics.geo-ph↗

arXiv2025

Deep Graph Neural Point Process For Learning Temporal Interactive Networks

Learning temporal interaction networks(TIN) is previously regarded as a coarse-grained multi-sequence prediction problem, ignoring the network topology structure influence. This paper addresses this limitation and a Deep Graph Neural Point Process(DGNPP) model for TIN is proposed. DGNPP consists of two key modules: the Node Aggregation Layer and the Self Attentive Layer. The Node Aggregation Layer captures topological structures to generate static representation for users and items, while the Self Attentive Layer dynamically updates embeddings over time. By incorporating both dynamic and static embeddings into the event intensity function and optimizing the model via maximum likelihood estimation, DGNPP predicts events and occurrence time effectively. Experimental evaluations on three public datasets demonstrate that DGNPP achieves superior performance in event prediction and time prediction tasks with high efficiency, significantly outperforming baseline models and effectively mitigating the limitations of prior approaches.

cs.LG↗

arXiv2025

Entanglement suppression and emergent symmetries in hadron scatterings

Recently entanglement suppression was proposed to be one potential origin of emergent symmetries. In this work, we extend this theoretical framework to accommodate particles with arbitrary spins and/or arbitrary group representations. As case studies, we discuss recent efforts to test the entanglement-suppression conjecture in two hadron systems that exhibit possible emergent symmetries. The first concerns interactions involving spin-3/2 baryons, where entanglement suppression gives rise to symmetries such as $\text{SU}(40)$ spin-flavor symmetry. The second system involves low-energy scattering of heavy mesons, where entanglement suppression leads to an enhancement of the inherent heavy-quark spin symmetry to a light-quark spin symmetry, predicting additional siblings for the prominent exotic double-charm meson $T_{cc}(3875)^+$. These predictions should be confronted against experimental data and lattice results to further test the minimal-entanglement conjecture.

hep-ph↗

arXiv2025

Superconducting gap in covalent bismuth dihydride BiH$_2$ under extreme conditions

Hydride superconductors at megabar pressures provide a promising platform for exploring room-temperature superconductivity. However, their superconducting gaps remain largely inaccessible to conventional spectroscopic due to diamond anvil cell constraints and minute sample dimensions. Here we develop a pulsed current method and apply it to covalent BiH$_2$ synthesized at 157--176 GPa. BiH$_2$ exhibits superconductivity at 58--70 K and upper critical fields of 11--17 T, substantially lower than those of many clathrate superhydrides, corresponding to a relatively long coherence length and an experimentally accessible critical current density. Short rectangular pulses minimize sustained Joule heating and enable currents up to 160 mA, allowing $J_c(T)$ to be measured in the low-temperature regime down to 2 K at 176 GPa. The normalized critical-current response remains reproducible between two measurement runs and is better described by a two-scale $s$-wave model than by single-gap $s$- or $d$-wave models, yielding effective energy scales of approximately 6.9 and 1.5 meV. Fully anisotropic Migdal--Eliashberg calculations yield a single highly anisotropic gap, suggesting that the two-gap behavior observed experimentally originates from gap anisotropy rather than two independent gaps. These results establish pulsed critical-current measurements as a practical gap-sensitive transport probe under extreme pressure and, with further increases in peak-current capability, provide a route toward investigating room-temperature hydrides such as La--Sc--H.

cond-mat.supr-con↗

arXiv2024

Discovery and inversion of the viscoelastic wave equation in inhomogeneous media

In scientific machine learning, the task of identifying partial differential equations accurately from sparse and noisy data poses a significant challenge. Current sparse regression methods may identify inaccurate equations on sparse and noisy datasets and are not suitable for varying coefficients. To address this issue, we propose a hybrid framework that combines two alternating direction optimization phases: discovery and embedding. The discovery phase employs current well-developed sparse regression techniques to preliminarily identify governing equations from observations. The embedding phase implements a recurrent convolutional neural network (RCNN), enabling efficient processes for time-space iterations involved in discretized forms of wave equation. The RCNN model further optimizes the imperfect sparse regression results to obtain more accurate functional terms and coefficients. Through alternating update of discovery-embedding phases, essential physical equations can be robustly identified from noisy and low-resolution measurements. To assess the performance of proposed framework, numerical experiments are conducted on various scenarios involving wave equation in elastic/viscoelastic and homogeneous/inhomogeneous media. The results demonstrate that the proposed method exhibits excellent robustness and accuracy, even when faced with high levels of noise and limited data availability in both spatial and temporal domains.

cs.LG↗

arXiv2024

Physics-informed Neural Networks with Fourier Features for Seismic Wavefield Simulation in Time-Domain Nonsmooth Complex Media

Physics-informed neural networks (PINNs) have great potential for flexibility and effectiveness in forward modeling and inversion of seismic waves. However, coordinate-based neural networks (NNs) commonly suffer from the "spectral bias" pathology, which greatly limits their ability to model high-frequency wave propagation in sharp and complex media. We propose a unified framework of Fourier feature physics-informed neural networks (FF-PINNs) for solving the time-domain wave equations. The proposed framework combines the stochastic gradient descent (SGD) strategy with an independently pre-trained wave velocity surrogate model to mitigate the singularity at the point source. The performance of the activation functions and gradient descent strategies are discussed through ablation experiments. In addition, we evaluate the accuracy comparison of Fourier feature mappings sampled from different families of distributions (Gaussian, Laplace, and uniform). The second-order paraxial approximation-based boundary conditions are incorporated into the loss function as a soft regularizer to eliminate spurious boundary reflections. Through the non-smooth Marmousi and Overthrust model cases, we emphasized the necessity of the absorbing boundary conditions (ABCs) constraints. The results of a series of numerical experiments demonstrate the accuracy and effectiveness of the proposed method for modeling high-frequency wave propagation in sharp and complex media.

physics.geo-ph↗

arXiv2024

Entanglement suppression and low-energy scattering of heavy mesons

Recently entanglement suppression was proposed to be one possible origin of emergent symmetries. Here we test this conjecture in the context of heavy meson scatterings. The low-energy interactions of $D^{(*)}\bar D^{(*)}$ and $D^{(*)} D^{(*)}$ are closely related to the hadronic molecular candidates $X(3872)$ and $T_{cc}(3875)^+$, respectively, and can be described by a nonrelativistic effective Lagrangian manifesting heavy-quark spin symmetry, which includes only constant contact potentials at leading order. We explore entanglement suppression in a tensor-product framework to treat both the isospin and spin degrees of freedom. Using the $X(3872)$ and $T_{cc}(3875)^+$ as inputs, we find that entanglement suppression indeed leads to an emergent symmetry, namely, a light-quark spin symmetry, and as such the $D^{(*)}\bar D^{(*)}$ or $D^{(*)} D^{(*)}$ interaction strengths for a given total isospin do not depend on the total angular momentum of light (anti)quarks. The $X(3872)$ and $T_{cc}(3875)^+$ are predicted to have five and one isoscalar partner, respectively, while the corresponding partner numbers derived solely from heavy-quark spin symmetry are three and one, respectively. The predictions need to be confronted with experimental data and lattice quantum chromodynamics results to further test the entanglement suppression conjecture.

hep-ph↗

arXiv2023

Large negative magnetoresistance and pseudogap phase in superconducting A15-type La$_4$H$_{23}$

High pressure plays a crucial role in the field of superconductivity. Compressed hydride superconductors are leaders in the race for a material that can conduct electricity without resistance at high or even room temperature. In the present work, we have discovered new lanthanum superhydride, cubic A15-type La$_4$H$_{23}$, with lower stabilization pressure compared to the reported $\textit{fcc}$ LaH$_{10}$. Superconducting La$_4$H$_{23}$ was obtained by laser heating of LaH$_3$ with ammonia borane at about 120 GPa. Transport measurements reveal the maximum critical temperature $\textit{T}$$_{C}$(onset) = 105 K and the critical field $\textit{H}$$_{C2}$(0) = 32 T at 118 GPa, as evidenced by the sharp drop of electrical resistance and the displacement of superconducting transitions in applied magnetic fields. Moreover, we provide evidence for unconventional transport associated with a pseudogap phase in La$_4$H$_{23}$ using pulsed magnetic fields up to 68 T. A large negative magnetoresistance in the non-superconducting state below 40 K, quasi $\textit{T}$-linear electrical resistance, and a sign-change of its temperature dependence mark the emergence of pseudogap in this hydride. Discovered lanthanum hydride is a new member of the A15 family of superconductors with $\textit{T}$$_C$ exceeding the boiling point of liquid nitrogen.

cond-mat.supr-con↗

arXiv2023

Physics Symbolic Learner for Discovering Ground-Motion Models Via NGA-West2 Database

Ground-motion model (GMM) is the basis of many earthquake engineering studies. In this study, a novel physics-informed symbolic learner (PISL) method based on the Nest Generation Attenuation-West2 database is proposed to automatically discover mathematical equation operators as symbols. The sequential threshold ridge regression algorithm is utilized to distill a concise and interpretable explicit characterization of complex systems of ground motions. In addition to the basic variables retrieved from previous GMMs, the current PISL incorporates two a priori physical conditions, namely, distance and amplitude saturation. GMMs developed using the PISL, an empirical regression method (ERM), and an artificial neural network (ANN) are compared in terms of residuals and extrapolation based on obtained data of peak ground acceleration and velocity. The results show that the inter- and intra-event standard deviations of the three methods are similar. The functional form of the PISL is more concise than that of the ERM and ANN. The extrapolation capability of the PISL is more accurate than that of the ANN. The PISL-GMM used in this study provide a new paradigm of regression that considers both physical and data-driven machine learning and can be used to identify the implied physical relationships and prediction equations of ground motion variables in different regions.

cs.LG↗

arXiv2022

SeismicNet: Physics-informed neural networks for seismic wave modeling in semi-infinite domain

There has been an increasing interest in integrating physics knowledge and machine learning for modeling dynamical systems. However, very limited studies have been conducted on seismic wave modeling tasks. A critical challenge is that these geophysical problems are typically defined in large domains (i.e., semi-infinite), which leads to high computational cost. In this paper, we present a novel physics-informed neural network (PINN) model for seismic wave modeling in semi-infinite domain without the nedd of labeled data. In specific, the absorbing boundary condition is introduced into the network as a soft regularizer for handling truncated boundaries. In terms of computational efficiency, we consider a sequential training strategy via temporal domain decomposition to improve the scalability of the network and solution accuracy. Moreover, we design a novel surrogate modeling strategy for parametric loading, which estimates the wave propagation in semin-infinite domain given the seismic loading at different locations. Various numerical experiments have been implemented to evaluate the performance of the proposed PINN model in the context of forward modeling of seismic wave propagation. In particular, we define diverse material distributions to test the versatility of this approach. The results demonstrate excellent solution accuracy under distinctive scenarios.

physics.geo-ph↗

arXiv2022

Enhancement of the superconducting critical temperature realized in the La-Ce-H system at moderate pressures

Covalent and ionic polyhydrides have become the two main camps in searching for the high-temperature superconductors under pressure. They have been considered as important platforms for exploring ternary or multiple hydrides in order to further increase the Tc or decrease the stabilization pressure. In this work, we successfully synthesized ternary hexagonal La-Ce polyhydrides stable in the pressure range of 95-130 GPa by laser-heating the La-Ce alloy (initial ratio La:Ce=2.5-3.5) in ammonia borane. Superconductivity at 176 K was strikingly preserved to about 100 GPa. The extrapolated upper critical field Hc2(0) reached 216 T at 100 GPa, the highest value among the synthesized polyhydrides. We also performed the contrast experiments and stabilized binary high-temperature superconducting LaHx with Tc-103 K at 78 GPa. In the pressure range of 95-130 GPa, the ternary hexagonal La-Ce-H system exhibits higher Tc than the binary La-H system, with the maximum difference of 100 K, and the compounds of both systems were synthesized at the same pressure and temperature conditions. These results clearly indicate that the discovered La-Ce-H system not only enriches the high-temperature superconducting hydrides but also realizes high-Tc at moderate pressures.

cond-mat.supr-con↗

arXiv2013

Higher order Sobol' indices

Sobol' indices measure the dependence of a high dimensional function on groups of variables defined on the unit cube $[0,1]^d$. They are based on the ANOVA decomposition of functions, which is an $L^2$ decomposition. In this paper we discuss generalizations of Sobol' indices which yield $L^p$ measures of the dependence of $f$ on subsets of variables. Our interest is in values $p>2$ because then variable importance becomes more about reaching the extremes of $f$. We introduce two methods. One based on higher order moments of the ANOVA terms and another based on higher order norms of a spectral decomposition of $f$, including Fourier and Haar variants. Both of our generalizations have representations as integrals over $[0,1]^{kd}$ for $k\ge 1$, allowing direct Monte Carlo or quasi-Monte Carlo estimation. We find that they are sensitive to different aspects of $f$, and thus quantify different notions of variable importance.

math.NA↗

arXiv2012

Efficient Processing of k Nearest Neighbor Joins using MapReduce

k nearest neighbor join (kNN join), designed to find k nearest neighbors from a dataset S for every object in another dataset R, is a primitive operation widely adopted by many data mining applications. As a combination of the k nearest neighbor query and the join operation, kNN join is an expensive operation. Given the increasing volume of data, it is difficult to perform a kNN join on a centralized machine efficiently. In this paper, we investigate how to perform kNN join using MapReduce which is a well-accepted framework for data-intensive applications over clusters of computers. In brief, the mappers cluster objects into groups; the reducers perform the kNN join on each group of objects separately. We design an effective mapping mechanism that exploits pruning rules for distance filtering, and hence reduces both the shuffling and computational costs. To reduce the shuffling cost, we propose two approximate algorithms to minimize the number of replicas. Extensive experiments on our in-house cluster demonstrate that our proposed methods are efficient, robust and scalable.

cs.DB↗