arXiv subjects

Yulin Xie

Publications and source records attributed to Yulin Xie.

5 recordsLinked to original sources

arXiv2026

Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers

Finite element (FE) modeling of safety-critical infrastructure such as bridge barriers requires high-fidelity nonlinear dynamic analysis, yet the current FE modeling process remains labor-intensive and lacks automation. This paper presents the Human-Enhanced Loop Modeling (HELM) framework, a collaborative human-agent protocol that decomposes long-sequence finite element modeling into discrete, visually verifiable checkpoints across geometry generation, boundary condition definition, and material assignment. The framework is demonstrated through a 20-case matrix of reinforced concrete bridge barriers under MASH TL-4 and TL-5 lateral loading conditions, interfacing specialized agents with two widely used commercial FE softwares, i.e., ANSYS and LS-PrePost. Experimental results show that HELM improves the baseline autonomous modeling success rate from 20% to 75%, with agent-level pass rates for geometry and boundary condition tasks approximately doubling. Error analysis reveals that spatial reasoning and algebraic logic limitations constitute the primary failure modes, underscoring the value of structured human-in-the-loop intervention for modeling automation. The complete agent design code and prompts are open-sourced and can be accessed at: https://github.com/SimAgentDev/Ansys-LSPP-AgentKit.

cs.AI↗

arXiv2026

Learning symplectic model reduction based on an approximation theorem of symplectic embeddings

High-dimensional Hamiltonian systems play a central role in many scientific and engineering disciplines, with dynamics that evolve on symplectic manifolds. Although deep learning provides powerful tools for constructing its low-dimensional surrogates from data, the intrinsic symplectic structure is easily destroyed during model reduction. As a result, a standard autoencoder may produce latent coordinates that do not support a Hamiltonian flow, leading to unstable long-time prediction. In this paper, we first establish a universal approximation theorem for symplectic embeddings. And based on the theory, we propose symplecticity-preserving autoencoders (SpAE), in which the decoder is parameterized as a symplectic embedding and the encoder is constructed as the corresponding symplectic projection. This architecture is expressive enough to approximate nonlinear symplectic embeddings and the corresponding symplectic projection, preserves the symplectic structure exactly by construction, and can be trained by standard unconstrained optimization, thereby improving both reconstruction and prediction accuracy. Extensive experiments on high-dimensional lattice and particle systems demonstrate the effectiveness of the proposed method.

cs.LG↗

arXiv2025

Spiking Neural Networks with Temporal Attention-Guided Adaptive Fusion for imbalanced Multi-modal Learning

Multimodal spiking neural networks (SNNs) hold significant potential for energy-efficient sensory processing but face critical challenges in modality imbalance and temporal misalignment. Current approaches suffer from uncoordinated convergence speeds across modalities and static fusion mechanisms that ignore time-varying cross-modal interactions. We propose the temporal attention-guided adaptive fusion framework for multimodal SNNs with two synergistic innovations: 1) The Temporal Attention-guided Adaptive Fusion (TAAF) module that dynamically assigns importance scores to fused spiking features at each timestep, enabling hierarchical integration of temporally heterogeneous spike-based features; 2) The temporal adaptive balanced fusion loss that modulates learning rates per modality based on the above attention scores, preventing dominant modalities from monopolizing optimization. The proposed framework implements adaptive fusion, especially in the temporal dimension, and alleviates the modality imbalance during multimodal learning, mimicking cortical multisensory integration principles. Evaluations on CREMA-D, AVE, and EAD datasets demonstrate state-of-the-art performance (77.55\%, 70.65\% and 97.5\%accuracy, respectively) with energy efficiency. The system resolves temporal misalignment through learnable time-warping operations and faster modality convergence coordination than baseline SNNs. This work establishes a new paradigm for temporally coherent multimodal learning in neuromorphic systems, bridging the gap between biological sensory processing and efficient machine intelligence.

cs.LG↗

arXiv2024

The Unisolvence of Lagrange Interpolation with Symmetric Interpolation Space and Nodes in High Dimension

High-dimensional Lagrange interpolation plays a pivotal role in finite element methods, where ensuring the unisolvence and symmetry of its interpolation space and nodes set is crucial. In this paper, we leverage group action and group representation theories to precisely delineate the conditions for unisolvence. We establish a necessary condition for unisolvence: the symmetry of the interpolation nodes set is determined by the given interpolation space. Our findings not only contribute to a deeper theoretical understanding but also promise practical benefits by reducing the computational overhead associated with identifying appropriate interpolation nodes.

math.NA↗

arXiv2022

Easily generating and absorbing waves using machine learning

High-order wave-making theories are becoming available but are limited to certain ranges of waves and wavemaker types in their applicability. Alternatively, machine learning can be considered to find nonlinear functional relationships. Therefore, this paper proposes a simple and universal framework for generating and absorbing waves based on machine learning. This framework trains neural networks to establish the transfer function between the free-surface elevation on the wavemaker and the wavemaker velocity. Significantly, penalty term and data augmentation techniques based on wave-making mechanisms are introduced to increase the generalization ability of neural networks, rather than pure data-driven. Therefore, once the target wave profiles in front of the wavemaker are given, it can realize generating waves and absorbing reflected waves at the same time. Taking piston and plunger wavemakers as examples, an in-house numerical solver is applied to simulate both wave generation and absorption. The simulated wave profiles and wave orbital velocities are validated with analytical solutions, showing that the proposed framework is effective at eliminating the re-reflection wave. Then, the validation for generating the solitary wave and the New-year wave is performed, indicating that the generated waves agree quite well with the desired wave elevation. The proposed framework can facilitate the wavemaker design in the future, and no complex theoretical derivation is required.

physics.flu-dyn↗