arXiv subjects

Mengying Xie

Publications and source records attributed to Mengying Xie.

9 recordsLinked to original sources

arXiv2026

Joint Distribution Alignment for Universal Domain Adaptation

Unsupervised domain adaptation (UDA) has been widely concerned in the fields of machine learning, pattern recognition, and computer vision. Traditional UDA learning usually assumes that the label spaces of the source and target domains are exactly the same and only needs to solve the problem of sample distribution drift existing between two domains. However, in real world applications, the label spaces between two domains may be different. In this case, there are both sample distribution drift and class spatial difference between domains, namely Universal Domain Adaptation (UniDA) learning scenario. At present, existing works rarely offer theoretical analysis for universal domain adaptation. In this paper, we provide an upper bound of the generalization error for universal domain adaptation. According to the proposed generalization error bound, we propose a novel UniDA algorithm called Joint Distribution Alignment for Universal Domain Adaptation (JAUA), which aligns the joint distributions by minimizing the distribution discrepancy calculated by Chi-Square divergence. Furthermore, we propose a progressive pseudo-labeling method to assign the pseudo labels to unlabeled target samples. The experiment results on six public image datasets demonstrate the superiority of JAUA in handling the UniDA problem.

cs.LG↗

arXiv2026

SG-Layout: Structured Scene Graph-Guided Layout Generation with LLMs

Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs). Existing LLMs often struggle to capture explicit geometric relationships and structural dependencies between objects. To address this issue, we propose SG-Layout, a graph-guided layout generation framework that explicitly incorporates structured spatial knowledge into LLMs. SG-Layout follows a two-stage training paradigm: (1) a graph-language feature alignment stage, where a relational graph encoder and a projector are trained to map scene-graph embeddings into the LLM's linguistic space; and (2) an instruction tuning stage, where LoRA-based adapters enable efficient fine-tuning for instruction-driven layout generation while keeping the backbone frozen. We evaluate SG-Layout on image layout generation, indoor scene synthesis and robotic object rearrangement tasks. Experimental results show that SG-Layout improves spatial reasoning accuracy and geometric consistency over the compact open-source backbone, with particularly clear advantages in relation-dense and compositionally complex scenes. These results highlight the effectiveness of graph-structured feature alignment for enhancing controllable layout generation.

cs.CV↗

arXiv2026

GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation

Articulated object manipulation is a unique challenge for service robots. Existing methods employ end-to-end policy learning, visionmotion planning, and large-language/visual-language model (LLM/VLM), but often overlook the diversity of articulated objects and the complexity of interactions between end-effector and handle, leading to limited generalization and destructive collisions. To address this, we propose GSAM, a generalizable and safe robotic framework for articulated object manipulation. Specifically, a vision-based perceiver generates the kinematic parameters. Considering that pre-trained markers in perceiver yield raw estimations that may deviate from commonsense, we present a f ine-tuned VLM-based refiner, using chain-of-thought (COT) commonsense reasoning to refine perception. To prevent destructive collisions, we design an interaction constraint function generator, integrating articulated object, interaction pose, and obstacle avoidance knowledge into a base. LLM then functionalize these constraints and apply them to trajectory and posture planning. A kinematic-aware manipulation planner verifies reachability for trajectory and posture. Experiments on 50 hinge tasks across 5 object categories and 50 randomly initialized end-effectorhandle configurations show that GSAM reduces standard deviation by 3.1% and improves manipulation success rate by 36.0% compared to the best baseline, respectively demonstrating the superior object generalization and interaction safety of GSAM in practical scenarios.

cs.RO↗

arXiv2025

UniRSCD: A Unified Novel Architectural Paradigm for Remote Sensing Change Detection

In recent years, remote sensing change detection has garnered significant attention due to its critical role in resource monitoring and disaster assessment. Change detection tasks exist with different output granularities such as BCD, SCD, and BDA. However, existing methods require substantial expert knowledge to design specialized decoders that compensate for information loss during encoding across different tasks. This not only introduces uncertainty into the process of selecting optimal models for abrupt change scenarios (such as disaster outbreaks) but also limits the universality of these architectures. To address these challenges, this paper proposes a unified, general change detection framework named UniRSCD. Building upon a state space model backbone, we introduce a frequency change prompt generator as a unified encoder. The encoder dynamically scans bitemporal global context information while integrating high-frequency details with low-frequency holistic information, thereby eliminating the need for specialized decoders for feature compensation. Subsequently, the unified decoder and prediction head establish a shared representation space through hierarchical feature interaction and task-adaptive output mapping. This integrating various tasks such as binary change detection and semantic change detection into a unified architecture, thereby accommodating the differing output granularity requirements of distinct change detection tasks. Experimental results demonstrate that the proposed architecture can adapt to multiple change detection tasks and achieves leading performance on five datasets, including the binary change dataset LEVIR-CD, the semantic change dataset SECOND, and the building damage assessment dataset xBD.

cs.CV↗

arXiv2024

Dynamics-Based Algorithm-Level Privacy Preservation for Push-Sum Average Consensus

In the intricate dance of multi-agent systems, achieving average consensus is not just vital--it is the backbone of their functionality. In conventional average consensus algorithms, all agents reach an agreement by individual calculations and sharing information with their respective neighbors. Nevertheless, the information interactions that occur in the communication network may make sensitive information be revealed. In this paper, we develop a new privacy-preserving average consensus method on unbalanced directed networks. Specifically, we ensure privacy preservation by carefully embedding randomness in mixing weights to confuse communications and introducing an extra auxiliary parameter to mask the state-updated rule in several initial iterations. In parallel, we exploit the intrinsic robustness of consensus dynamics to guarantee that the average consensus is precisely achieved. Theoretical results demonstrate that the designed algorithms can converge linearly to the exact average consensus value and can guarantee privacy preservation of agents against both honest-but-curious and eavesdropping attacks. The designed algorithms are fundamentally different compared to differential privacy based algorithms that enable privacy preservation via sacrificing consensus performance. Finally, numerical experiments validate the correctness of the theoretical findings.

cs.MA↗

arXiv2019

Understanding the effect of porosity on the polarisation-field response of ferroelectric materials

This paper combines experimental and modelling studies to provide a detailed examination of the influence of porosity volume fraction and morphology on the polarisation-electric field response of ferroelectric materials. The broadening of the electric field distribution and a decrease in the electric field experienced by the ferroelectric ceramic medium due to the presence of low-permittivity pores is examined and its implications on the shape of the hysteresis loop, remnant polarisation and coercive field is discussed. The variation of coercive field with porosity level is seen to be complex and is attributed to two competing mechanisms where at high porosity levels the influence of the broadening of the electric field distribution dominates, while at low porosity levels an increase in the compliance of the matrix is more important. This new approach to understanding these materials enables the seemingly conflicting observations in the existing literature to be clarified and provides an effective approach to interpret the influence of pore fraction and morphology on the polarisation behaviour of ferroelectrics. Such information provides new insights in the interpretation of the physical properties of porous ferroelectric materials to inform future effort in the design of ferroelectric materials for piezoelectric sensor, actuator, energy harvesting, and transducer applications.

cond-mat.mtrl-sci↗

arXiv2019

High piezoelectric sensitivity and hydrostatic figures of merit in unidirectional porous ferroelectric ceramics fabricated by freeze casting

High performance lead zirconate titanate (PZT) ceramics with aligned porosity for sensing applications were fabricated by an ice-templating method. To demonstrate the enhanced properties of these materials and their potential for sensor and hydrophone applications, the piezoelectric voltage constants hydrostatic parameters and AC conductivity as a function of the porosity in directions both parallel and perpendicular to the freezing temperature gradient were studied. As the porosity level was increased, PZT poled parallel to the freezing direction exhibited the highest coefficients, and hydrostatic figures of merit compared to the dense and PZT poled perpendicular to the freezing direction. This work demonstrates that piezoelectric ceramics produced with aligned pores by freeze casting are a promising candidate for a range of sensor applications and the polarisation orientation relative to the freezing direction can be used to tailor the microstructure and optimise sensitivity for sensor and hydrostatic transducer applications.

physics.app-ph↗

arXiv2019

Energy harvesting from coupled bending-twisting oscillations in carbon-fibre reinforced polymer laminates

The energy harvesting capability of resonant harvesting structures, such as piezoelectric cantilever beams, can be improved by utilizing coupled oscillations that generate favourable strain mode distributions. In this work, we present the first demonstration of the use of a laminated carbon fibre reinforced polymer to create cantilever beams that undergo coupled bending-twisting oscillations for energy harvesting applications. Piezoelectric layers that operate in bending and shear mode are attached to the bend-twist coupled beam surface at locations of maximum bending and torsional strains in the first mode of vibration to fully exploit the strain distribution along the beam. Modelling of this new bend-twist harvesting system is presented, which compares favourably with experimental results. It is demonstrated that the variety of bend and torsional modes of the harvesters can be utilized to create a harvester that operates over a wider range of frequencies and such multi-modal device architectures provides a unique approach to tune the frequency response of resonant harvesting systems.

cond-mat.mtrl-sci↗

arXiv2019

Enhanced pyroelectric and piezoelectric properties of PZT with aligned porosity for energy harvesting applications

This paper demonstrates the significant benefits of exploiting highly aligned porosity in piezoelectric and pyroelectric materials for improved energy harvesting performance. Porous lead zirconate (PZT) ceramics with aligned pore channels and varying fractions of porosity were manufactured in a water-based suspension using freeze casting. The aligned porous PZT ceramics were characterized in detail for both piezoelectric and pyroelectric properties and their energy harvesting performance figures of merit were assessed parallel and perpendicular to the freezing direction. As a result of the introduction of porosity into the ceramic microstrucutre, high piezoelectric and pyroelectric harvesting figures of merits were achieved for porous freeze-cast PZT compared to dense PZT due to the reduced permittivity and volume specific heat capacity. Experimental results were compared to parallel and series analytical models with good agreement and the PZT with porosity aligned parallel to the freezing direction exhibited the highest piezoelectric and pyroelectric harvesting response; this was a result of the enhanced interconnectivity of the ferroelectric material along the poling direction and reduced fraction of unpoled material that leads to a higher polarization. A complete thermal energy harvesting system, composed of an parallel-aligned PZT harvester element and an AC/DC converter successfully demonstrated by charging a storage capacitor. The maximum energy density generated by the 60 vol.% porous parallel-connected PZT when subjected to thermal oscillations was 1653 μJ/cm3 respectively, which was 374% higher than that of the dense PZT with an energy density of 446 μJ/cm3. The results are of benefit for the design and manufacture of high performance porous pyroelectric and piezoelectric materials in devices for energy harvesting and sensor applications.

physics.app-ph↗