arXiv subjects

Siyuan Xing

Publications and source records attributed to Siyuan Xing.

7 recordsLinked to original sources

arXiv2026

Large Language Model-Assisted Superconducting Qubit Experiments

Superconducting circuits have demonstrated significant potential in quantum information processing and quantum sensing. Implementing novel control and measurement sequences for superconducting qubits is often a complex and time-consuming process, requiring extensive expertise in both the underlying physics and the specific hardware and software. In this work, we introduce a framework that leverages a large language model (LLM) to automate qubit control and measurement. Specifically, our framework conducts experiments by generating and invoking schema-less tools on demand via a knowledge base on instrumental usage and experimental procedures. We showcase this framework with two experiments: an autonomous resonator characterization and a direct reproduction of a quantum non-demolition (QND) characterization of a superconducting qubit from literature. This framework enables rapid deployment of standard control-and-measurement protocols and facilitates implementation of novel experimental procedures, offering a more flexible and user-friendly paradigm for controlling complex quantum hardware.

quant-ph↗

arXiv2026

BRepMAE: Self-Supervised Masked BRep Autoencoders for Machining Feature Recognition

We propose a masked self-supervised learning framework, called BRepMAE, for automatically extracting a valuable representation of the input computer-aided design (CAD) model to recognize its machining features. Representation learning is conducted on a large-scale, unlabeled CAD model dataset using the geometric Attributed Adjacency Graph (gAAG) representation, derived from the boundary representation (BRep). The self-supervised network is a masked graph autoencoder (MAE) that focuses on reconstructing geometries and attributes of BRep facets, rather than graph structures. After pre-training, we fine-tune a network that contains both the encoder and a task-specific classification network for machining feature recognition (MFR). In the experiments, our fine-tuned network achieves high recognition rates with only a small amount of data (e.g., 0.1% of the training data), significantly enhancing its practicality in real-world (or private) scenarios where only limited data is available. Compared with other MFR methods, our fine-tuned network achieves a significant improvement in recognition rate with the same amount of training data, especially when the number of training samples is limited.

cs.GR↗

arXiv2025

Harnessing Multimodal Large Language Models for Personalized Product Search with Query-aware Refinement

Personalized product search (PPS) aims to retrieve products relevant to the given query considering user preferences within their purchase histories. Since large language models (LLM) exhibit impressive potential in content understanding and reasoning, current methods explore to leverage LLM to comprehend the complicated relationships among user, query and product to improve the search performance of PPS. Despite the progress, LLM-based PPS solutions merely take textual contents into consideration, neglecting multimodal contents which play a critical role for product search. Motivated by this, we propose a novel framework, HMPPS, for \textbf{H}arnessing \textbf{M}ultimodal large language models (MLLM) to deal with \textbf{P}ersonalized \textbf{P}roduct \textbf{S}earch based on multimodal contents. Nevertheless, the redundancy and noise in PPS input stand for a great challenge to apply MLLM for PPS, which not only misleads MLLM to generate inaccurate search results but also increases the computation expense of MLLM. To deal with this problem, we additionally design two query-aware refinement modules for HMPPS: 1) a perspective-guided summarization module that generates refined product descriptions around core perspectives relevant to search query, reducing noise and redundancy within textual contents; and 2) a two-stage training paradigm that introduces search query for user history filtering based on multimodal representations, capturing precise user preferences and decreasing the inference cost. Extensive experiments are conducted on four public datasets to demonstrate the effectiveness of HMPPS. Furthermore, HMPPS is deployed on an online search system with billion-level daily active users and achieves an evident gain in A/B testing.

cs.MM↗

arXiv2025

Mitigating cosmic ray-like correlated events with a modular quantum processor

Quantum processors based on superconducting qubits are being scaled to larger qubit numbers, enabling the implementation of small-scale quantum error correction codes. However, catastrophic chip-scale correlated errors have been observed in these processors, attributed to e.g. cosmic ray impacts, which challenge conventional error-correction codes such as the surface code. These events are characterized by a temporary but pronounced suppression of the qubit energy relaxation times. Here, we explore the potential for modular quantum computing architectures to mitigate such correlated energy decay events. We measure cosmic ray-like events in a quantum processor comprising a motherboard and two flip-chip bonded daughterboard modules, each module containing two superconducting qubits. We monitor the appearance of correlated qubit decay events within a single module and across the physically separated modules. We find that while decay events within one module are strongly correlated (over $85\%$), events in separate modules only display $\sim 2\%$ correlations. We also report coincident decay events in the motherboard and in either of the two daughterboard modules, providing further insight into the nature of these decay events. These results suggest that modular architectures, combined with bespoke error correction codes, offer a promising approach for protecting future quantum processors from chip-scale correlated errors.

quant-ph↗

arXiv2024

Learning Traveling Solitary Waves Using Separable Gaussian Neural Networks

In this paper, we apply a machine-learning approach to learn traveling solitary waves across various families of partial differential equations (PDEs). Our approach integrates a novel interpretable neural network (NN) architecture, called Separable Gaussian Neural Networks (SGNN) into the framework of Physics-Informed Neural Networks (PINNs). Unlike the traditional PINNs that treat spatial and temporal data as independent inputs, the present method leverages wave characteristics to transform data into the so-called co-traveling wave frame. This adaptation effectively addresses the issue of propagation failure in PINNs when applied to large computational domains. Here, the SGNN architecture demonstrates robust approximation capabilities for single-peakon, multi-peakon, and stationary solutions within the (1+1)-dimensional, $b$-family of PDEs. In addition, we expand our investigations, and explore not only peakon solutions in the $ab$-family but also compacton solutions in (2+1)-dimensional, Rosenau-Hyman family of PDEs. A comparative analysis with MLP reveals that SGNN achieves comparable accuracy with fewer than a tenth of the neurons, underscoring its efficiency and potential for broader application in solving complex nonlinear PDEs.

nlin.PS↗

arXiv2023

Separable Gaussian Neural Networks: Structure, Analysis, and Function Approximations

The Gaussian-radial-basis function neural network (GRBFNN) has been a popular choice for interpolation and classification. However, it is computationally intensive when the dimension of the input vector is high. To address this issue, we propose a new feedforward network - Separable Gaussian Neural Network (SGNN) by taking advantage of the separable property of Gaussian functions, which splits input data into multiple columns and sequentially feeds them into parallel layers formed by uni-variate Gaussian functions. This structure reduces the number of neurons from O(N^d) of GRBFNN to O(dN), which exponentially improves the computational speed of SGNN and makes it scale linearly as the input dimension increases. In addition, SGNN can preserve the dominant subspace of the Hessian matrix of GRBFNN in gradient descent training, leading to a similar level of accuracy to GRBFNN. It is experimentally demonstrated that SGNN can achieve 100 times speedup with a similar level of accuracy over GRBFNN on tri-variate function approximations. The SGNN also has better trainability and is more tuning-friendly than DNNs with RuLU and Sigmoid functions. For approximating functions with complex geometry, SGNN can lead to three orders of magnitude more accurate results than a RuLU-DNN with twice the number of layers and the number of neurons per layer.

cs.LG↗

arXiv2022

Breathers in lattices with alternating strain-hardening and strain-softening interactions

This work focuses on the study of time-periodic solutions, including breathers, in a nonlinear lattice consisting of elements whose contacts alternate between strain-hardening and strain-softening. The existence, stability, and bifurcation structure of such solutions, as well as the system dynamics in the presence of damping and driving are studied systematically. It is found that the linear resonant peaks in the system bend toward the frequency gap in the presence of nonlinearity. The time-periodic solutions that lie within the frequency gap compare well to Hamiltonian breathers if the damping and driving are small. In the Hamiltonian limit of the problem, we use a multiple scale analysis to derive a Nonlinear Schrödinger (NLS) equation to construct both acoustic and optical breathers. The latter compare very well with the numerically obtained breathers in the Hamiltonian limit.

nlin.PS↗