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

Xin Du

Xin Du contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
eess.SYSystems and ControlDistributed, Parallel, and Cluster ComputingMachine LearningComputer Visionmath.DSmath.OCSocial and Information NetworksArtificial IntelligenceComputation and LanguageComputational Engineering, Finance, and Sciencecond-mat.dis-nnCryptography and SecurityInformation RetrievalMultiagent Systemsnlin.CD

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
16works
0followers
16topics
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

16 published item(s)

preprint2026arXiv

CEE: An Inference-Time Jailbreak Defense for Embodied Intelligence via Subspace Concept Rotation

Large language models (LLMs) are widely used for task understanding and action planning in embodied intelligence (EI) systems, but their adoption substantially increases vulnerability to jailbreak attacks. While recent work explores inference-time defenses, existing methods rely on static interventions on intermediate representations, which often degrade generation quality and impair adherence to task instructions, reducing system usability in EI settings. We propose a dynamic defense framework. For each EI inference request, we dynamically construct a task-specific safety-semantic subspace, project its hidden state to the most relevant direction, and apply SLERP rotation for adaptive safety control. At comparable defense success rates, our method preserves generation quality, improves usability, reduces tuning cost, and strengthens robustness in EI scenarios.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Escaping Mode Collapse in LLM Generation via Geometric Regulation

Mode collapse is a persistent challenge in generative modeling and appears in autoregressive text generation as behaviors ranging from explicit looping to gradual loss of diversity and premature trajectory convergence. We take a dynamical-systems view and reinterpret mode collapse as reduced state-space accessibility caused by *geometric collapse*: during generation, the model's internal trajectory becomes confined to a low-dimensional region of its representation space. This implies mode collapse is not purely a token-level phenomenon and cannot be reliably solved by symbolic constraints or probability-only decoding heuristics. Guided by this perspective, we propose *Reinforced Mode Regulation* (RMR), a lightweight, online state-space intervention that regulates dominant self-reinforcing directions in the Transformer value cache (implemented as low-rank damping). Across multiple large language models, RMR substantially reduces mode collapse and enables stable, high-quality generation at extremely low entropy rates (down to 0.8 nats/step), whereas standard decoding typically collapses near 2.0 nats/step.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

A Low-latency Communication Design for Brain Simulations

Brain simulation, as one of the latest advances in artificial intelligence, facilitates better understanding about how information is represented and processed in the brain. The extreme complexity of human brain makes brain simulations only feasible upon high-performance computing platforms. Supercomputers with a large number of interconnected graphical processing units (GPUs) are currently employed for supporting brain simulations. Therefore, high-throughput low-latency inter-GPU communications in supercomputers play a crucial role in meeting the performance requirements of brain simulation as a highly time-sensitive application. In this paper, we first provide an overview of the current parallelizing technologies for brain simulations using multi-GPU architectures. Then, we analyze the challenges to communications for brain simulation and summarize guidelines for communication design to address such challenges. Furthermore, we propose a partitioning algorithm and a two-level routing method to achieve efficient low-latency communications in multi-GPU architecture for brain simulation. We report experiment results obtained on a supercomputer with 2,000 GPUs for simulating a brain model with 10 billion neurons to show that our approach can significantly improve communication performance. We also discuss open issues and identify some research directions for low-latency communication design for brain simulations.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Multi-Curve Translator for High-Resolution Photorealistic Image Translation

The dominant image-to-image translation methods are based on fully convolutional networks, which extract and translate an image's features and then reconstruct the image. However, they have unacceptable computational costs when working with high-resolution images. To this end, we present the Multi-Curve Translator (MCT), which not only predicts the translated pixels for the corresponding input pixels but also for their neighboring pixels. And if a high-resolution image is downsampled to its low-resolution version, the lost pixels are the remaining pixels' neighboring pixels. So MCT makes it possible to feed the network only the downsampled image to perform the mapping for the full-resolution image, which can dramatically lower the computational cost. Besides, MCT is a plug-in approach that utilizes existing base models and requires only replacing their output layers. Experiments demonstrate that the MCT variants can process 4K images in real-time and achieve comparable or even better performance than the base models on various photorealistic image-to-image translation tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

NLOS Error Mitigation Using Weighted Least Squares and Kalman Filter in UWB Positioning

In wireless positioning systems, non-line-of-sight (NLOS) is a challenging problem. NLOS causes great ranging bias and location error, so NLOS mitigation is essential for high accuracy positioning. In this letter, we propose the Weighted-Least-Squares Robust Kalman Filter (WLS-RKF) for NLOS identification and mitigation. WLS-RKF employs a hypothesis test based on Mahalanobis distance for NLOS identification, and updates the corresponding Kalman filter using the WLS solution. It requires no prior knowledge about NLOS distribution or signal features. We perform simulations and experiments for ultra-wideband (UWB) positioning in various scenarios. The results confirm that WLS-RKF effectively mitigates NLOS error and achieves 5cm positioning accuracy.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Scientific Workflows in Heterogeneous Edge-Cloud Computing: A Data Placement Strategy Based on Reinforcement learning

The heterogeneous edge-cloud computing paradigm can provide an optimal solution to deploy scientific workflows compared to cloud computing or other traditional distributed computing environments. Owing to the different sizes of scientific datasets and the privacy issue concerning some of these datasets, it is essential to find a data placement strategy that can minimize data transmission time. Some state-of-the-art data placement strategies combine edge computing and cloud computing to distribute scientific datasets. However, the dynamic distribution of newly generated datasets to appropriate datacenters and exiting the spent datasets are still a challenge during workflows execution. To address this challenge, this study not only constructs a data placement model that includes shared datasets within individual and among multiple workflows across various geographical regions, but also proposes a data placement strategy (DYM-RL-DPS) based on algorithms of two stages. First, during the build-time stage of workflows, we use the discrete particle swarm optimization algorithm with differential evolution to pre-allocate initial datasets to proper datacenters. Then, we reformulate the dynamic datasets distribution problem as a Markov decision process and provide a reinforcement learning-based approach to learn the optimal strategy in the runtime stage of scientific workflows. Through simulating heterogeneous edge-cloud computing environments, we designed comprehensive experiments to demonstrate the superiority of DYM-RL-DPS. The results of our strategy can effectively reduce the data transmission time as compared to other strategies.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Vision Checklist: Towards Testable Error Analysis of Image Models to Help System Designers Interrogate Model Capabilities

Using large pre-trained models for image recognition tasks is becoming increasingly common owing to the well acknowledged success of recent models like vision transformers and other CNN-based models like VGG and Resnet. The high accuracy of these models on benchmark tasks has translated into their practical use across many domains including safety-critical applications like autonomous driving and medical diagnostics. Despite their widespread use, image models have been shown to be fragile to changes in the operating environment, bringing their robustness into question. There is an urgent need for methods that systematically characterise and quantify the capabilities of these models to help designers understand and provide guarantees about their safety and robustness. In this paper, we propose Vision Checklist, a framework aimed at interrogating the capabilities of a model in order to produce a report that can be used by a system designer for robustness evaluations. This framework proposes a set of perturbation operations that can be applied on the underlying data to generate test samples of different types. The perturbations reflect potential changes in operating environments, and interrogate various properties ranging from the strictly quantitative to more qualitative. Our framework is evaluated on multiple datasets like Tinyimagenet, CIFAR10, CIFAR100 and Camelyon17 and for models like ViT and Resnet. Our Vision Checklist proposes a specific set of evaluations that can be integrated into the previously proposed concept of a model card. Robustness evaluations like our checklist will be crucial in future safety evaluations of visual perception modules, and be useful for a wide range of stakeholders including designers, deployers, and regulators involved in the certification of these systems. Source code of Vision Checklist would be open for public use.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Frequency Limited $\mathcal{H}_2$ Optimal Model Reduction of Large-Scale Sparse Dynamical Systems

We mainly consider the frequency limited $\mathcal{H}_2$ optimal model order reduction of large-scale sparse generalized systems. For this purpose we need to solve two Sylvester equations. This paper proposes efficient algorithm to solve them efficiently. The ideas are also generalized to index-1 descriptor systems. Numerical experiments are carried out using Python Programming Language and the results are presented to demonstrate the approximation accuracy and computational efficiency of the proposed techniques.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Iterative Rational Krylov Algorithms for model reduction of a class of constrained structural dynamic system with Engineering applications

This paper discusses model order reduction of large sparse second-order index-3 differential algebraic equations (DAEs) by applying Iterative Rational Krylov Algorithm (IRKA). In general, such DAEs arise in constraint mechanics, multibody dynamics, mechatronics and many other branches of sciences and technologies. By deecting the algebraic equations the second-order index-3 system can be altered into an equivalent standard second-order system. This can be done by projecting the system onto the null space of the constraint matrix. However, creating the projector is computationally expensive and it yields huge bottleneck during the implementation. This paper shows how to find a reduce order model without projecting the system onto the null space of the constraint matrix explicitly. To show the efficiency of the theoretical works we apply them to several data of second-order index-3 models and experimental resultants are discussed in the paper.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

V2V-Based Task Offloading and Resource Allocation in Vehicular Edge Computing Networks

In the research and application of vehicle ad hoc networks (VANETs), it is often assumed that vehicles obtain cloud computing services by accessing to roadside units (RSUs). However, due to the problems of insufficient construction quantity, limited communication range and overload of calculation load of roadside units, the calculation mode relying only on vehicle to roadside units is difficult to deal with complex and changeable calculation tasks. In this paper, when the roadside unit is missing, the vehicle mobile unit is regarded as a natural edge computing node to make full use of the excess computing power of mobile vehicles and perform the offloading task of surrounding mobile vehicles in time. In this paper, the OPFTO framework is designed, an improved task allocation algorithm HGSA is proposed, and the pre-filtering process is designed with full consideration of the moving characteristics of vehicles. In addition, vehicle simulation experiments show that the proposed strategy has the advantages of low delay and high accuracy compared with other task scheduling strategies, which provides a reference scheme for the construction of Urban Intelligent Transportation in the future.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage

User identity linkage across social networks is an essential problem for cross-network data mining. Since network structure, profile and content information describe different aspects of users, it is critical to learn effective user representations that integrate heterogeneous information. This paper proposes a novel framework with INformation FUsion and Neighborhood Enhancement (INFUNE) for user identity linkage. The information fusion component adopts a group of encoders and decoders to fuse heterogeneous information and generate discriminative node embeddings for preliminary matching. Then, these embeddings are fed to the neighborhood enhancement component, a novel graph neural network, to produce adaptive neighborhood embeddings that reflect the overlapping degree of neighborhoods of varying candidate user pairs. The importance of node embeddings and neighborhood embeddings are weighted for final prediction. The proposed method is evaluated on real-world social network data. The experimental results show that INFUNE significantly outperforms existing state-of-the-art methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Basketball Player's Value Evaluation by a Networks-based Variant Parameter Hidden Markov Model

Determining the value of basketball players through analyzing the players' behavior is important for the managers of modern basketball teams. However, conventional methods always utilize isolated statistical data, leading to ineffective and inaccurate evaluations. Existing models based on dynamic network theory offer major improvements to the results of such evaluations, but said models remain imprecise because they focus merely on evaluating the values of individual players rather than considering them within their current teams. To solve this problem, we propose an analysis and evaluation model based on networks and a hidden Markov model. To the best of our knowledge, we are the first to combine a network form representing the players who are playing with the use of a hidden Markov model to mine the network and generate the desired results. Applying our approach to SportVU data collected from the National Basketball Association shows that this analysis and evaluation model can effectively analyze the performance of each player in a game and provides an assistive tool for team managers.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Causal Discovery from Incomplete Data: A Deep Learning Approach

As systems are getting more autonomous with the development of artificial intelligence, it is important to discover the causal knowledge from observational sensory inputs. By encoding a series of cause-effect relations between events, causal networks can facilitate the prediction of effects from a given action and analyze their underlying data generation mechanism. However, missing data are ubiquitous in practical scenarios. Directly performing existing casual discovery algorithms on partially observed data may lead to the incorrect inference. To alleviate this issue, we proposed a deep learning framework, dubbed Imputated Causal Learning (ICL), to perform iterative missing data imputation and causal structure discovery. Through extensive simulations on both synthetic and real data, we show that ICL can outperform state-of-the-art methods under different missing data mechanisms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Frequency-Limited Pseudo-Optimal Rational Krylov Algorithm for Power System Reduction

In this paper, a computationally efficient frequency-limited model reduction algorithm is presented for large-scale interconnected power systems. The algorithm generates a reduced order model which not only preserves the electromechanical modes of the original power system but also satisfies a subset of the first-order optimality conditions for H2;! model reduction problem within the desired frequency interval. The reduced-order model accurately captures the oscillatory behavior of the original power system and provides a good time- and frequency-domain accuracy. The proposed algorithm enables fast simulation, analysis, and damping controller design for the original large-scale power system. The efficacy of the proposed algorithm is validated on benchmark power system examples.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Time- and frequency-limited H2-optimal model order reduction of bilinear control systems

In the time- and frequency-limited model order reduction, a reduced-order approximation of the original high-order model is sought to ensure superior accuracy in some desired time and frequency intervals. We first consider the time-limited H2-optimal model order reduction problem for bilinear control systems and derive first-order optimality conditions that a local optimum reduced-order model should satisfy. We then propose a heuristic algorithm that generates a reduced-order model, which tends to achieve these optimality conditions. The frequency-limited and the time-limited H2-pseudo-optimal model reduction problems are also considered wherein we restrict our focus on constructing a reduced-order model that satisfies a subset of the respective optimality conditions for the local optimum. Two new algorithms have been proposed that enforce two out of four optimality conditions on the reduced-order model upon convergence. The algorithms are tested on three numerical examples to validate the theoretical results presented in the paper. The numerical results confirm the efficacy of the proposed algorithms.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Time-limited pseudo-optimal H$_2$-model order reduction

A model order reduction algorithm is presented that generates a reduced-order model of the original high-order model, which ensures high-fidelity within the desired time interval. The reduced model satisfies a subset of the first-order optimality conditions for time-limited H$_2$-model reduction problem. The algorithm uses a computationally efficient Krylov subspace-based framework to generate the reduced model, and it is applicable to large-scale systems. The reduced-order model is parameterized to enforce a subset of the first-order optimality conditions in an iteration-free way. We also propose an adaptive framework of the algorithm, which ensures a monotonic decay in error irrespective of the choice of interpolation points and tangential directions. The efficacy of the algorithm is validated on benchmark model reduction problems.

0 citations0 reviewsNo code linkedOpen access