arXiv subjects

Wanxin Li

Publications and source records attributed to Wanxin Li.

At least 19 recordsLinked to original sources

arXiv2026

BotDirector: Robot Storytelling Across the Symmetrical Reality with Multi-modal Interactions

Robot storytelling offers a unique blend of technological innovation and creative expression that engages children in unprecedented ways. However, the technical aspects are often too complicated for children. We propose an interactive system that facilitates robot storytelling with tangible and natural language interactions. Children arrange the playground with their own stuff and create narratives with an LLM agent. The created narratives are transformed into a motion sequence based on the map and characters, and the motions are executed by self-navigating swarm robots. This system enhances robot storytelling with flexible scenarios, enabling young children to create robot dramas with everyday objects.

cs.RO↗

arXiv2026

Scalable Identification and Prioritization of Requisition-Specific Personal Competencies Using Large Language Models

AI-powered recruitment tools are increasingly adopted in personnel selection, yet they struggle to capture the requisition (req)-specific personal competencies (PCs) that distinguish successful candidates beyond job categories. We propose a large language model (LLM)-based approach to identify and prioritize req-specific PCs from reqs. Our approach integrates dynamic few-shot prompting, reflection-based self-improvement, similarity-based filtering, and multi-stage validation. Applied to a dataset of Program Manager reqs, our approach correctly identifies the highest-priority req-specific PCs with an average accuracy of 0.76, approaching human expert inter-rater reliability, and maintains a low out-of-scope rate of 0.07.

cs.CL↗

arXiv2025

Wasserstein projection distance for fairness testing of regression models

Fairness testing evaluates whether a model satisfies a specified fairness criterion across different groups, yet most research has focused on classification models, leaving regression models underexplored. This paper introduces a framework for fairness testing in regression models, leveraging Wasserstein distance to project data distribution and focusing on expectation-based criteria. Upon categorizing fairness criteria for regression, we derive a Wasserstein projection test statistic from dual reformulation, and derive asymptotic bounds and limiting distributions, allowing us to formulate both a hypothesis-testing procedure and an optimal data perturbation method to improve fairness while balancing accuracy. Experiments on synthetic data demonstrate that the proposed hypothesis-testing approach offers higher specificity compared to permutation-based tests. To illustrate its potential applications, we apply our framework to two case studies on real data, showing (1) statistically significant gender disparities that appear on student performance data across multiple models, and (2) significant unfairness between pollution areas under multiple fairness criteria affecting housing price data, robust to different group divisions, with feature-level analysis identifying spatial and socioeconomic drivers.

cs.LG↗

arXiv2025

The Pragmatic Mind of Machines: Tracing the Emergence of Pragmatic Competence in Large Language Models

Current large language models (LLMs) have demonstrated emerging capabilities in social intelligence tasks, including implicature resolution and theory-of-mind reasoning, both of which require substantial pragmatic understanding. However, how LLMs acquire this pragmatic competence throughout the training process remains poorly understood. In this work, we introduce ALTPRAG, a dataset grounded in the pragmatic concept of alternatives, to evaluate whether LLMs at different training stages can accurately infer nuanced speaker intentions. Each instance pairs two equally plausible yet pragmatically divergent continuations and requires the model to (i) infer the speaker's intended meaning and (ii) explain when and why a speaker would choose one utterance over its alternative, thus directly probing pragmatic competence through contrastive reasoning. We systematically evaluate 22 LLMs across 3 key training stages: after pre-training, supervised fine-tuning (SFT), and preference optimization, to examine the development of pragmatic competence. Our results show that even base models exhibit notable sensitivity to pragmatic cues, which improves consistently with increases in model and data scale. Additionally, SFT and RLHF contribute further gains, particularly in cognitive-pragmatic scenarios. These findings highlight pragmatic competence as an emergent and compositional property of LLM training and offer new insights for aligning models with human communicative norms.

cs.CL↗

arXiv2024

KG-Rank: Enhancing Large Language Models for Medical QA with Knowledge Graphs and Ranking Techniques

Large language models (LLMs) have demonstrated impressive generative capabilities with the potential to innovate in medicine. However, the application of LLMs in real clinical settings remains challenging due to the lack of factual consistency in the generated content. In this work, we develop an augmented LLM framework, KG-Rank, which leverages a medical knowledge graph (KG) along with ranking and re-ranking techniques, to improve the factuality of long-form question answering (QA) in the medical domain. Specifically, when receiving a question, KG-Rank automatically identifies medical entities within the question and retrieves the related triples from the medical KG to gather factual information. Subsequently, KG-Rank innovatively applies multiple ranking techniques to refine the ordering of these triples, providing more relevant and precise information for LLM inference. To the best of our knowledge, KG-Rank is the first application of KG combined with ranking models in medical QA specifically for generating long answers. Evaluation on four selected medical QA datasets demonstrates that KG-Rank achieves an improvement of over 18% in ROUGE-L score. Additionally, we extend KG-Rank to open domains, including law, business, music, and history, where it realizes a 14% improvement in ROUGE-L score, indicating the effectiveness and great potential of KG-Rank.

cs.CL↗

arXiv2023

B^2SFL: A Bi-level Blockchained Architecture for Secure Federated Learning-based Traffic Prediction

Federated Learning (FL) is a privacy-preserving machine learning (ML) technology that enables collaborative training and learning of a global ML model based on aggregating distributed local model updates. However, security and privacy guarantees could be compromised due to malicious participants and the centralized FL server. This article proposed a bi-level blockchained architecture for secure federated learning-based traffic prediction. The bottom and top layer blockchain store the local model and global aggregated parameters accordingly, and the distributed homomorphic-encrypted federated averaging (DHFA) scheme addresses the secure computation problems. We propose the partial private key distribution protocol and a partially homomorphic encryption/decryption scheme to achieve the distributed privacy-preserving federated averaging model. We conduct extensive experiments to measure the running time of DHFA operations, quantify the read and write performance of the blockchain network, and elucidate the impacts of varying regional group sizes and model complexities on the resulting prediction accuracy for the online traffic flow prediction task. The results indicate that the proposed system can facilitate secure and decentralized federated learning for real-world traffic prediction tasks.

cs.CR↗

arXiv2023

Traffic Prediction using Artificial Intelligence: Review of Recent Advances and Emerging Opportunities

Traffic prediction plays a crucial role in alleviating traffic congestion which represents a critical problem globally, resulting in negative consequences such as lost hours of additional travel time and increased fuel consumption. Integrating emerging technologies into transportation systems provides opportunities for improving traffic prediction significantly and brings about new research problems. In order to lay the foundation for understanding the open research challenges in traffic prediction, this survey aims to provide a comprehensive overview of traffic prediction methodologies. Specifically, we focus on the recent advances and emerging research opportunities in Artificial Intelligence (AI)-based traffic prediction methods, due to their recent success and potential in traffic prediction, with an emphasis on multivariate traffic time series modeling. We first provide a list and explanation of the various data types and resources used in the literature. Next, the essential data preprocessing methods within the traffic prediction context are categorized, and the prediction methods and applications are subsequently summarized. Lastly, we present primary research challenges in traffic prediction and discuss some directions for future research.

cs.LG↗

arXiv2023

Aggregated Zero-knowledge Proof and Blockchain-Empowered Authentication for Autonomous Truck Platooning

Platooning technologies enable trucks to drive cooperatively and automatically, providing benefits including less fuel consumption, greater road capacity, and safety. This paper introduces an aggregated zero-knowledge proof and blockchain-empowered system for privacy-preserving identity verification in the mixed fleet platooning environment. The correctness proof and the security analysis of the proposed authentication scheme are provided, highlighting its increased security and fast performance in comparison to a single-proof design. The blockchain performs the role of verifier within the authentication scheme, reducing unnecessary communication overhead. Moreover, the blockchain improves system resilience by providing fault tolerance to the decentralized verification process. Platooning records are stored directly on the digital ledger to guarantee data immutability and integrity, while the programmable access control policies ensure data privacy. The experimental results demonstrate that the proposed approach can perform authentication on the order of milliseconds, regardless of the number of proofs, highlighting feasibility for real-world deployment in truck platooning.

cs.CR↗

arXiv2023

A Hybrid Blockchain-Edge Architecture for Electronic Health Records Management with Attribute-based Cryptographic Mechanisms

This paper presents a hybrid blockchain-edge architecture for managing Electronic Health Records (EHRs) with attribute-based cryptographic mechanisms. The architecture introduces a novel attribute-based signature aggregation (ABSA) scheme and multi-authority attribute-based encryption (MA-ABE) integrated with Paillier homomorphic encryption (HE) to protect patients' anonymity and safeguard their EHRs. All the EHR activities and access control events are recorded permanently as blockchain transactions. We develop the ABSA module on Hyperledger Ursa cryptography library, MA-ABE module on OpenABE toolset, and blockchain network on Hyperledger Fabric. We measure the execution time of ABSA's signing and verification functions, MA-ABE with different access policies and homomorphic encryption schemes, and compare the results with other existing blockchain-based EHR systems. We validate the access activities and authentication events recorded in blockchain transactions and evaluate the transaction throughput and latency using Hyperledger Caliper. The results show that the performance meets real-world scenarios' requirements while safeguarding EHR and is robust against unauthorized retrievals.

cs.CR↗

arXiv2023

BFRT: Blockchained Federated Learning for Real-time Traffic Flow Prediction

Accurate real-time traffic flow prediction can be leveraged to relieve traffic congestion and associated negative impacts. The existing centralized deep learning methodologies have demonstrated high prediction accuracy, but suffer from privacy concerns due to the sensitive nature of transportation data. Moreover, the emerging literature on traffic prediction by distributed learning approaches, including federated learning, primarily focuses on offline learning. This paper proposes BFRT, a blockchained federated learning architecture for online traffic flow prediction using real-time data and edge computing. The proposed approach provides privacy for the underlying data, while enabling decentralized model training in real-time at the Internet of Vehicles edge. We federate GRU and LSTM models and conduct extensive experiments with dynamically collected arterial traffic data shards. We prototype the proposed permissioned blockchain network on Hyperledger Fabric and perform extensive tests using virtual machines to simulate the edge nodes. Experimental results outperform the centralized models, highlighting the feasibility of our approach for facilitating privacy-preserving and decentralized real-time traffic flow prediction.

cs.DC↗

arXiv2023

A Hierarchical and Location-aware Consensus Protocol for IoT-Blockchain Applications

Blockchain-based IoT systems can manage IoT devices and achieve a high level of data integrity, security, and provenance. However, incorporating existing consensus protocols in many IoT systems limits scalability and leads to high computational cost and consensus latency. In addition, location-centric characteristics of many IoT applications paired with limited storage and computing power of IoT devices bring about more limitations, primarily due to the location-agnostic designs in blockchains. We propose a hierarchical and location-aware consensus protocol (LH-Raft) for IoT-blockchain applications inspired by the original Raft protocol to address these limitations. The proposed LH-Raft protocol forms local consensus candidate groups based on nodes' reputation and distance to elect the leaders in each sub-layer blockchain. It utilizes a threshold signature scheme to reach global consensus and the local and global log replication to maintain consistency for blockchain transactions. To evaluate the performance of LH-Raft, we first conduct an extensive numerical analysis based on the proposed reputation mechanism and the candidate group formation model. We then compare the performance of LH-Raft against the classical Raft protocol from both theoretical and experimental perspectives. We evaluate the proposed threshold signature scheme using Hyperledger Ursa cryptography library to measure various consensus nodes' signing and verification time. Experimental results show that the proposed LH-Raft protocol is scalable for large IoT applications and significantly reduces the communication cost, consensus latency, and agreement time for consensus processing.

cs.CR↗

arXiv2023

P-CFT: A Privacy-preserving and Crash Fault Tolerant Consensus Algorithm for Permissioned Blockchains

Consensus algorithms play a critical role in blockchains and directly impact their performance. During consensus processing, nodes need to validate and order the pending transactions into a new block, which requires verifying the application-specific data encapsulated within a transaction. This exposes the underlying data to the consensus nodes, presenting privacy concerns. Existing consensus algorithms focus on realizing application security and performance goals, but lack privacy-by-design properties or are resource-heavy and intended for securing permissionless blockchain networks. In this paper, we propose P-CFT, a zero-knowledge and crash fault tolerant consensus algorithm for permissioned blockchains. The proposed consensus algorithm provides inherent data privacy directly to the consensus layer, while still providing guarantees of crash fault tolerance. We conduct experiments using the Hyperledger Ursa cryptographic library, and the results show promise for integrating P-CFT into existing permissioned blockchain systems requiring privacy-preserving and crash fault tolerant features.

cs.CR↗

arXiv2023

A Location-based and Hierarchical Framework for Fast Consensus in Blockchain Networks

Blockchain-based IoT systems can manage IoT devices and achieve a high level of data integrity, security, and provenance. However, incorporating the existing consensus protocols in many IoT systems limits scalability and leads to high computational cost and network latency. We propose a hierar-chical and location-aware consensus protocol for IoI-blockchain applications inspired by the original Raft protocol to address these limitations. The proposed consensus protocol generates the consensus candidate groups based on nodes' individual reputation and distance information to elect the leader in each sub-layer blockchain and uses our threshold signature scheme to reach global consensus. Experimental results show that the proposed consensus protocol is scalable for large IoT applications and significantly reduces the communication cost, network latency, and agreement time by more than 50% compared with the Raft protocol for consensus processing.

cs.CR↗

arXiv2023

Location-aware Verification for Autonomous Truck Platooning Based on Blockchain and Zero-knowledge Proof

Platooning technologies enable trucks to drive cooperatively and automatically, which bring benefits including less fuel consumption, more road capacity and safety. In order to establish trust during dynamic platoon formation, ensure vehicular data integrity, and guard platoons against potential attackers, it is pivotal to verify any given vehicle's identity information before granting it access to join a platoon. To address this concern in dynamic truck platooning, we present a novel location-aware and privacy-preserving verification protocol based on zero-knowledge proof and permissioned blockchain. By performing the verification process within the spatially-local area defined by a given platoon, our system can provide lower latency and communication overhead compared to a location-agnostic blockchain system. We prototype the proposed system and perform benchmark tests on the Hyperledger platform. The experimental results show that our system is suitable for real-world truck platooning.

cs.NI↗

arXiv2022

Electric field enhancement of pool boiling of dielectric fluids on pillar-structured surfaces: A lattice Boltzmann study

In this paper, by using a phase-change lattice Boltzmann (LB) model coupled with an electric field model, we numerically investigate the performance and enhancement mechanism of pool boiling of dielectric fluids on pillar-structured surfaces under an electric field. The numerical investigation reveals that applying an electric field causes both positive and negative influences on the pool boiling of dielectric fluids on pillar-structured surfaces. It is found that, under the action of an electric field, the electric force prevents the bubbles nucleated in the channels from crossing the edges of the pillar tops. On the one hand, such an effect results in the bubble coalescence in the channels and blocks the paths of liquid supply for the channels, which leads to the deterioration of pool boiling in the medium-superheat regime. On the other hand, it prevents the coalescence between the bubbles in the channels and those on the pillar tops, which suppresses the formation of a continuous vapor film and therefore delays the occurrence of boiling crisis. Meanwhile, the electric force can promote the departure of the bubbles on the pillar tops. Accordingly, the critical heat flux (CHF) can be improved. Based on the revealed mechanism, wettability-modified regions are applied to the pillar tops for further enhancing the boiling heat transfer. It is shown that the boiling performance on pillar-structured surfaces can be enhanced synergistically with the CHF being increased by imposing an electric field and the maximum heat transfer coefficient being improved by applying mixed wettability to the pillar-structured surfaces.

physics.flu-dyn↗

arXiv2020

Blockchain-enabled Identity Verification for Safe Ridesharing Leveraging Zero-Knowledge Proof

The on-demand mobility market, including ridesharing, is becoming increasingly important with e-hailing fares growing at a rate of approximately 130% per annum since 2013. By increasing utilization of existing vehicles and empty seats, ridesharing can provide many benefits including reduced traffic congestion and environmental impact from vehicle usage and production. However, the safety of riders and drivers has become of paramount concern and a method for privacy-preserving identity verification between untrusted parties is essential for protecting users. To this end, we propose a novel privacy-preserving identity verification system, extending zero-knowledge proof (ZKP) and blockchain for use in ridesharing applications. We design a permissioned blockchain network to perform the ZKP verification of a driver's identity, which also acts as an immutable ledger to store ride logs and ZKP records. For the ZKP module, we design a protocol to facilitate user verification without requiring the exchange of any private information. We prototype the proposed system on the Hyperledger Fabric platform, with the Hyperledger Ursa cryptography library, and conduct extensive experimentation. To measure the prototype's performance, we utilize the Hyperledger Caliper benchmark tool to perform extensive analysis and the results show that our system is suitable for use in real-world ridesharing applications.

cs.CR↗

arXiv2020

Attribute-based Multi-Signature and Encryption for EHR Management: A Blockchain-based Solution

The global Electronic Health Record (EHR) market is growing dramatically and has already hit $31.5 billion in 2018. To safeguard the security of EHR data and privacy of patients, fine-grained information access and sharing mechanisms are essential for EHR management. This paper proposes a hybrid architecture of blockchain and edge nodes to facilitate EHR management. In this architecture, we utilize attribute-based multi-signature (ABMS) scheme to authenticate user's signatures without revealing the sensitive information and multi-authority attribute-based encryption (ABE) scheme to encrypt EHR data which is stored on the edge node. We develop the blockchain module on Hyperledger Fabric platform and the ABMS module on Hyperledger Ursa library. We measure the signing and verifying time of the ABMS scheme under different settings, and experiment with the authentication events and access activities which are logged as transactions in blockchain.

cs.CR↗

arXiv2019

A Blockchain-Based Architecture for Traffic Signal Control Systems

Ever-growing incorporation of connected vehicle (CV) technologies into intelligent traffic signal control systems bring about significant data security issues in the connected vehicular networks. This paper presents a novel decentralized and secure by design architecture for connected vehicle data security, which is based on the emerging blockchain paradigm. In a simulation study, we applied this architecture to defend the Intelligent Traffic Signal System (I-SIG), a USDOT approved CV pilot program, against congestion attacks. The results show the performance of the proposed architecture for the traffic signal control system.

cs.NI↗