arXiv subjects

Xinrui Liu

Publications and source records attributed to Xinrui Liu.

10 recordsLinked to original sources

arXiv2026

LabDex: A Hierarchical Benchmark for Dexterous Manipulation in Laboratories

Autonomous laboratories hold great promise for accelerating scientific discovery. To achieve this vision, robots are supposed to dexterously manipulate diverse labware and instruments and execute long-horizon, state-dependent experimental procedures. Yet existing benchmarks do not jointly capture dexterous hand use, real-world laboratory interactions, and multi-stage experimental procedures, limiting systematic training and evaluation. To bridge this gap, we introduce LabDex, a large-scale real-world dataset and benchmark for dexterous manipulation in chemistry laboratories, organized around a hierarchical task taxonomy spanning atomic skills, compositional tasks, and long-horizon experiments. First, LabDex is cross-platform and, for the first time, unifies real-world and simulation platforms under a common framework, providing standardized task definitions, demonstrations, and evaluation protocols. Second, LabDex is large-scale and systematically organizes chemistry laboratory operations into three interconnected levels: Atomic Skills, which characterize fundamental dexterous manipulation capabilities; Compositional Skills; and Long-Horizon Laboratory Workflows. This hierarchical design not only supports the evaluation of end-task performance, but also enables the analysis of how fundamental dexterous skills compose and influence more complex laboratory operations. We conduct cross-level evaluations of representative robot learning methods in both real-world and simulation environments. The experimental results validate the effectiveness of the LabDex task design and demonstration data, and show that the benchmark supports the training and systematic evaluation of existing robotic policies across laboratory dexterous manipulation tasks at different levels, providing a foundation for further research and development of autonomous laboratory robots.

cs.RO↗

arXiv2025

Robustness of Bound States in the Continuum in Bilayer Structures against Symmetry Breaking

We investigate the robustness of bound states in the continuum (BICs) in a bilayer dielectric rod array against geometric and material perturbations. Our analysis focuses on both symmetry-protected and Fabry-Pérot BICs, examining their transformation into quasi-BICs under three structural modifications: (i) in-plane displacement of one layer, which breaks the C$_2$ symmetry of the system; (ii) introduction of material losses that break time-reversal symmetry; and (iii) variation in the interlayer distance, which preserves structural symmetry. In particular, we demonstrate that material losses inevitably induce radiation in Fabry-Pérot BICs via second-order perturbation processes, converting them into quasi-BICs, while symmetry-protected BICs remain non-radiative. We further show that, despite the inherent instability of BICs under symmetry-breaking effects, their resilience can be significantly enhanced through proper design. Both Fabry-Pérot and symmetry-protected BICs exhibit exponentially weak sensitivity to C$_2$-breaking perturbations as the interlayer distance increases. Finally, we show that additional FP-BICs emerge under oblique incidence, originating from the interference of two high-Q quasi-BICs near the symmetry-protected ones. Our findings pave the way for the development of BIC-based photonic devices with improved robustness against fabrication imperfections, environmental variations, and material losses.

physics.optics↗

arXiv2025

TABSurfer: a Hybrid Deep Learning Architecture for Subcortical Segmentation

Subcortical segmentation remains challenging despite its important applications in quantitative structural analysis of brain MRI scans. The most accurate method, manual segmentation, is highly labor intensive, so automated tools like FreeSurfer have been adopted to handle this task. However, these traditional pipelines are slow and inefficient for processing large datasets. In this study, we propose TABSurfer, a novel 3D patch-based CNN-Transformer hybrid deep learning model designed for superior subcortical segmentation compared to existing state-of-the-art tools. To evaluate, we first demonstrate TABSurfer's consistent performance across various T1w MRI datasets with significantly shorter processing times compared to FreeSurfer. Then, we validate against manual segmentations, where TABSurfer outperforms FreeSurfer based on the manual ground truth. In each test, we also establish TABSurfer's advantage over a leading deep learning benchmark, FastSurferVINN. Together, these studies highlight TABSurfer's utility as a powerful tool for fully automated subcortical segmentation with high fidelity.

eess.IV↗

arXiv2023

Parameterized proximal-gradient algorithms for L1/L2 sparse signal recovery

The ratio of L1 and L2 norms (L1/L2), serving as a sparse promoting function, receives considerable attentions recently due to its effectiveness for sparse signal recovery. In this paper, we propose an L1/L2 based penalty model for recovering sparse signals from noiseless or noisy observations. It is proven that stationary points of the proposed problem tend to those of the elliptically constrained L1/L2 minimization problem as the smoothing parameter goes to zero. Moreover, inspired by the parametric approach for the fractional programming, we design a parameterized proximal-gradient algorithm (PPGA) as well as its line search counterpart (PPGA_L) for solving the proposed model. The closed-form solution of the involved proximity operator is derived, which enable the efficiency of the proposed algorithms. We establish the global convergence of the entire sequences generated by PPGA and PPGA_L with monotone objective values by taking advantage of the fact that the objective of the proposed model is a KL function. Numerical experiments show the efficiency of the proposed algorithms over the state-of-the-art methods in both noiseless and noisy sparse signal recovery problems.

math.OC↗

arXiv2023

Stealthy Low-frequency Backdoor Attack against Deep Neural Networks

Deep neural networks (DNNs) have gain its popularity in various scenarios in recent years. However, its excellent ability of fitting complex functions also makes it vulnerable to backdoor attacks. Specifically, a backdoor can remain hidden indefinitely until activated by a sample with a specific trigger, which is hugely concealed. Nevertheless, existing backdoor attacks operate backdoors in spatial domain, i.e., the poisoned images are generated by adding additional perturbations to the original images, which are easy to detect. To bring the potential of backdoor attacks into full play, we propose low-pass attack, a novel attack scheme that utilizes low-pass filter to inject backdoor in frequency domain. Unlike traditional poisoned image generation methods, our approach reduces high-frequency components and preserve original images' semantic information instead of adding additional perturbations, improving the capability of evading current defenses. Besides, we introduce "precision mode" to make our backdoor triggered at a specified level of filtering, which further improves stealthiness. We evaluate our low-pass attack on four datasets and demonstrate that even under pollution rate of 0.01, we can perform stealthy attack without trading off attack performance. Besides, our backdoor attack can successfully bypass state-of-the-art defending mechanisms. We also compare our attack with existing backdoor attacks and show that our poisoned images are nearly invisible and retain higher image quality.

cs.CR↗

arXiv2023

Towards Invisible Backdoor Attacks in the Frequency Domain against Deep Neural Networks

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By injecting malicious data into the training set, an adversary can plant the backdoor into the original model. The backdoor can remain hidden indefinitely until activated by a sample with a specific trigger, which is hugely concealed, bringing serious security risks to critical applications. However, one main limitation of current backdoor attacks is that the trigger is often visible to human perception. Therefore, it is crucial to study the stealthiness of backdoor triggers. In this paper, we propose a novel frequency-domain backdooring technique. In particular, our method aims to add a backdoor trigger in the frequency domain of original images via Discrete Fourier Transform, thus hidding the trigger. We evaluate our method on three benchmark datasets: MNIST, CIFAR-10 and Imagenette. Our experiments show that we can simultaneously fool human inspection and DNN models. We further apply two image similarity evaluation metrics to illustrate that our method adds the most subtle perturbation without compromising attack success rate and clean sample accuracy.

cs.CR↗

arXiv2022

NDGGNET-A Node Independent Gate based Graph Neural Networks

Graph Neural Networks (GNNs) is an architecture for structural data, and has been adopted in a mass of tasks and achieved fabulous results, such as link prediction, node classification, graph classification and so on. Generally, for a certain node in a given graph, a traditional GNN layer can be regarded as an aggregation from one-hop neighbors, thus a set of stacked layers are able to fetch and update node status within multi-hops. For nodes with sparse connectivity, it is difficult to obtain enough information through a single GNN layer as not only there are only few nodes directly connected to them but also can not propagate the high-order neighbor information. However, as the number of layer increases, the GNN model is prone to over-smooth for nodes with the dense connectivity, which resulting in the decrease of accuracy. To tackle this issue, in this thesis, we define a novel framework that allows the normal GNN model to accommodate more layers. Specifically, a node-degree based gate is employed to adjust weight of layers dynamically, that try to enhance the information aggregation ability and reduce the probability of over-smoothing. Experimental results show that our proposed model can effectively increase the model depth and perform well on several datasets.

cs.LG↗

arXiv2021

Gaussian graphical models with graph constraints for magnetic moment interaction in high entropy alloys

This article is motivated by studying the interaction of magnetic moments in high entropy alloys (HEAs), which plays an important role in guiding HEA designs in materials science. While first principles simulations can capture magnetic moments of individual atoms, explicit models are required to analyze their interactions. This is essentially an inverse covariance matrix estimation problem. Unlike most of the literature on graphical models, the inverse covariance matrix possesses inherent structural constraints encompassing node types, topological distance of nodes, and partially specified conditional dependence patterns. The present article is, to our knowledge, the first to consider such intricate structures in graphical models. In particular, we introduce graph constraints to formulate these structures that arise from domain knowledge and are critical for interpretability, which leads to a Bayesian conditional autoregressive model with graph constraints (CARGO) for structured inverse covariance matrices. The CARGO method enjoys efficient implementation with a modified Gauss-Seidel scheme through proximity operators for closed-form posterior exploration. We establish algorithmic convergence for the proposed algorithm under a verifiable stopping criterion. Simulations show competitive performance of CARGO relative to several other methods and confirm our convergence analysis. In a novel real data application to HEAs, the proposed methods lead to data-driven quantification and interpretation of magnetic moment interactions with high tractability and transferability.

stat.ME↗

arXiv2020

Mission schedule of agile satellites based on Proximal Policy Optimization Algorithm

Mission schedule of satellites is an important part of space operation nowadays, since the number and types of satellites in orbit are increasing tremendously and their corresponding tasks are also becoming more and more complicated. In this paper, a mission schedule model combined with Proximal Policy Optimization Algorithm(PPO) is proposed. Different from the traditional heuristic planning method, this paper incorporate reinforcement learning algorithms into it and find a new way to describe the problem. Several constraints including data download are considered in this paper.

cs.AI↗

arXiv2019

Formation of gigahertz pulse train by chirped terahertz pulses interference

The development of multiplexing information transmission technology in the THz band may accelerate the arrival of the 6G era. In this paper, has demonstrated the feasibility of forming a sequence of subpulses in the temporal domain and the corresponding quasidiscrete spectrum in the THz frequency range. It is shown that despite the fact that the THz pulse has an exponential chirp, there is a "linkage relation" between spectrum and temporal structures of the THz pulse train. This fact can be used for encoding information in THz pulses for implementation in 6G communication systems in the future.

physics.optics↗