BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Xiaohong Zhang

Xiaohong Zhang contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine Learningmath.COArtificial IntelligenceComputation and LanguageComputer Visioneess.SPGraphicsInformation TheoryLogic in Computer Sciencemath.ITmath.LORoboticsSound

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
8works
0followers
13topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

8 published item(s)

preprint2026arXiv

Overcoming the Intrinsic Performance Limitations of MEMS IMU via Diffusion-Based Generative Learning

Inertial measurement units (IMUs) are fundamental sensing components in multi-source integrated navigation systems, and their performance directly determines the accuracy and reliability of solutions. However, the precision of low-cost IMUs is inherently constrained by hardware limitations. Recently, generative artificial intelligence has demonstrated remarkable capability in modeling complex data distributions and reconstructing high-fidelity signals. Motivated by this, we propose a diffusion-based generative learning framework for synthesizing high-fidelity virtual IMU data from low-cost IMU measurements. Specifically, a conditional diffusion model based on a U-Net architecture is constructed, where high-grade IMU measurements are utilized as ground-truth priors and low-cost IMU measurements are employed as conditional inputs. The virtual IMU data generated by the model is used for subsequent navigation and localization tasks. Experimental results demonstrate that the generated virtual IMU data significantly outperform the original low-cost IMU measurements in both positioning and attitude estimation. Furthermore, we transfer the model to airborne mapping experiments, where the proposed method produces thinner and more consistent point clouds. Overall, the proposed framework breaks the performance limits of low-cost IMU and demonstrates the potential of diffusion-based generative learning for virtual high-grade IMU data.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars

Speech-driven gestures and facial animations are fundamental to expressive digital avatars in games, virtual production, and interactive media. However, existing methods are either limited to a single modality for audio motion alignment, failing to fully utilize the potential of massive human motion data, or are constrained by the representation ability and throughput of multimodal models, which makes it difficult to achieve high-quality motion generation or real-time performance. We present UMo, a unified sparse motion modeling architecture for real-time co-speech avatars, which processes text, audio, and motion tokens within a unified formulation. Leveraging a spatially sparse Mixture-of-Experts framework and a temporally sparse, keyframe-centric design, UMo efficiently performs real-time dense reconstruction, enabling temporally coherent and high-fidelity animation generation for both facial expressions and gestures. Furthermore, we implement a multi-stage training strategy with targeted audio augmentation to enhance acoustic diversity and semantic consistency. Consequently, UMo preserves fine-grained speech-motion alignment even under strict latency constraints. Extensive quantitative and qualitative evaluations show that UMo achieves better output quality under low latency and real-time performance constraints, offering a practical solution for high-fidelity real-time co-speech avatars.

0 citations0 reviewsNo code linkedOpen access
preprint2025arXiv

QoSBERT: An Uncertainty-Aware Approach based on Pre-trained Language Models for Service Quality Prediction

Accurate prediction of Quality of Service (QoS) metrics is fundamental for selecting and managing cloud based services. Traditional QoS models rely on manual feature engineering and yield only point estimates, offering no insight into the confidence of their predictions. In this paper, we propose QoSBERT, the first framework that reformulates QoS prediction as a semantic regression task based on pre trained language models. Unlike previous approaches relying on sparse numerical features, QoSBERT automatically encodes user service metadata into natural language descriptions, enabling deep semantic understanding. Furthermore, we integrate a Monte Carlo Dropout based uncertainty estimation module, allowing for trustworthy and risk-aware service quality prediction, which is crucial yet underexplored in existing QoS models. QoSBERT applies attentive pooling over contextualized embeddings and a lightweight multilayer perceptron regressor, fine tuned jointly to minimize absolute error. We further exploit the resulting uncertainty estimates to select high quality training samples, improving robustness in low resource settings. On standard QoS benchmark datasets, QoSBERT achieves an average reduction of 11.7% in MAE and 6.7% in RMSE for response time prediction, and 6.9% in MAE for throughput prediction compared to the strongest baselines, while providing well calibrated confidence intervals for robust and trustworthy service quality estimation. Our approach not only advances the accuracy of service quality prediction but also delivers reliable uncertainty quantification, paving the way for more trustworthy, data driven service selection and optimization.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Fractional revival on non-cospectral vertices

Perfect state transfer and fractional revival can be used to move information between pairs of vertices in a quantum network. While perfect state transfer has received a lot of attention, fractional revival is newer and less studied. One problem is to determine the differences between perfect state transfer and fractional revival. If perfect state transfer occurs between two vertices in a graph, the vertices must be cospectral. Further if there is perfect state transfer between vertices $a$ and $b$ in a graph, there cannot be perfect state transfer from $a$ to any other vertex. No examples of unweighted graphs with fractional revival between non-cospectral vertices were known; here we give an infinite family of such graphs. No examples of unweighted graphs where the pairs involved in fractional revival overlapped were known; we give examples of such graphs as well.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Partial Residuated Implications Derived from Partial Triangular Norms and Partial Residuated Lattices

In this paper, we reveal some relations between fuzzy logic and quantum logic, and mainly study the partial residuated implications (PRIs) derived from partial triangular norms (partial t-norms) and partial residuated lattices (PRLs), and expand some results in the article "material implication in lattice effect algebra". Firstly, according to the concept of partial triangular norms given by Borzooei, we introduce the connection between lattice effect algebra and partial t-norms, and prove that partial operations in any commutative quasiresiduated lattice are partial t-norms. Secondly, we give the general form of partial residuated implications and the concept of partial fuzzy implications (PFIs), and the condition that partial residuated implication is a fuzzy implication is given. We also prove that each partial residuated implication is a partial fuzzy implication. Thirdly, we propose the partial residuated lattice and study their basic properties, to discuss the corresponding relationship between PRLs and lattice effect algebras (LEAs), to further reveal the relationship between LEAs and residuated partial algebras. In addition, like the definition of partial t-norms, we also propose the concepts of partial triangular conorms (partial t-conorms) and corresponding partial co-residuated lattices (PcRLs). Finally, based on partial residuated lattices, we give the definition of well partial residuated lattices (wPRLs), study the filter of well partial residuated lattices, and then construct quotient structure of partial residuated lattices.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Semi-overlap Functions and Novel Fuzzy Reasoning Algorithms with Applications

It is worth noticing that a fuzzy conjunction and its corresponding fuzzy implication can form a residual pair if and only if it is left-continuous. In order to get a more general result related on residual implications that induced by aggregation functions, we relax the definition of general overlap functions, more precisely, removing its right-continuous, and then introduce a new kind of aggregation functions, which called semi-overlap functions. Subsequently, we study some of their related algebraic properties and investigate their corresponding residual implications. Moreover, serval scholars have provided kinds of methods for fuzzy modus ponens (FMP,for short) problems so far, such as Zadeh's compositional rule of inference (CRI, for short), Wang's triple I method (TIM, for short) and the quintuple implication principle (QIP, for short). Compared with CRI and TIM methods, QIP method has some advantages in solving FMP problems, in this paper, we further consider the QIP method for FMP problems and prove that it satisfies the reducibility of multiple-rules fuzzy reasoning. Finally, we propose a new classification algorithm that based on semi-overlap functions and QIP method, which called SO5I-FRC algorithm. Through the comparative tests, the average accuracy of SO5I-FRC algorithm is higher than FARC-HD algorithm. The experimental results indicate that semi-overlap functions and QIP method have certain advantages and a wide range of applications in classification problems.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Hadamard diagonalizable graphs of order at most 36

If the Laplacian matrix of a graph has a full set of orthogonal eigenvectors with entries $\pm1$, then the matrix formed by taking the columns as the eigenvectors is a Hadamard matrix and the graph is said to be Hadamard diagonalizable. In this article, we prove that if $n=8k+4$ the only possible Hadamard diagonalizable graphs are $K_n$, $K_{n/2,n/2}$, $2K_{n/2}$, and $nK_1$, and we develop an efficient computation for determining all graphs diagonalized by a given Hadamard matrix of any order. Using these two tools, we determine and present all Hadamard diagonalizable graphs up to order 36. Note that it is not even known how many Hadamard matrices there are of order 36.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization

Graph representation learning based on graph neural networks (GNNs) can greatly improve the performance of downstream tasks, such as node and graph classification. However, the general GNN models do not aggregate node information in a hierarchical manner, and can miss key higher-order structural features of many graphs. The hierarchical aggregation also enables the graph representations to be explainable. In addition, supervised graph representation learning requires labeled data, which is expensive and error-prone. To address these issues, we present an unsupervised graph representation learning method, Unsupervised Hierarchical Graph Representation (UHGR), which can generate hierarchical representations of graphs. Our method focuses on maximizing mutual information between "local" and high-level "global" representations, which enables us to learn the node embeddings and graph embeddings without any labeled data. To demonstrate the effectiveness of the proposed method, we perform the node and graph classification using the learned node and graph embeddings. The results show that the proposed method achieves comparable results to state-of-the-art supervised methods on several benchmarks. In addition, our visualization of hierarchical representations indicates that our method can capture meaningful and interpretable clusters.

0 citations0 reviewsNo code linkedOpen access