arXiv subjects

Fei Hao

Publications and source records attributed to Fei Hao.

10 recordsLinked to original sources

arXiv2026

Embodied CAD: Solver-Grounded LLM Agents for Parametric B-Rep Assembly Modeling

Large language models can write plausible CAD scripts, but reliable industrial CAD modeling requires more than syntactically valid code: every feature, placement, and assembly relation must be accepted by an exact geometric kernel while remaining editable as parametric boundary representation geometry. We present Embodied CAD, solver-grounded LLM agents for parametric B-Rep assembly modeling. Instead of generating a complete script in one pass, the agent iteratively selects actions from a stratified L0-L4 CAD skill library, resolves them into typed geometric operations, executes them in a CAD backend, and uses solver feedback to plan, repair, and learn. The framework combines action grammar constraints, deterministic parameter resolution, and solver-derived rewards for supervised warm-up and GRPO-style refinement. We evaluate Embodied CAD on multi-step mechanical, industrial equipment, and mold-oriented assembly tasks using solver-aligned metrics: executable rate, skill accuracy, operation-family accuracy, exact policy accuracy, and task completion success. The results show that solver-grounded planning executes all strong-planner workflows in the current benchmark, while learned controllers reach high executable rates and expose the remaining gap between valid tool calls and exact long-horizon policy prediction.

cs.AI↗

arXiv2025

SARC: Sentiment-Augmented Deep Role Clustering for Fake News Detection

Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

cs.CL↗

arXiv2025

Appointed-Time Fault-Tolerant Control for Flexible Hypersonic Vehicles with Unmeasurable States Independent of Initial Errors

This article aims to derive a practical tracking control algorithm for flexible air-breathing hypersonic vehicles (FAHVs) with lumped disturbances, unmeasurable states and actuator failures. Based on the framework of the backstepping technique, an appointed-time fault-tolerant protocol independent of initial errors is proposed. Firstly, a new type of a state observer is constructed to reconstruct the unmeasurable states. Then, an error transformation function is designed to achieve prescribed performance control that does not depend on the initial tracking error. To deal with the actuator failures, practical fixed-time neural network observers are established to provide the estimation of the lumped disturbances. Finally, the proposed control strategy can ensure the practical fixed-time convergence of the closed-loop system, thereby greatly enhancing the transient performance. The proposed method addresses the challenges of ensuring real-time measurement accuracy for angle of attack and flight path angle in hypersonic vehicles, coupled with potential sudden actuator failures, effectively overcoming the drawback of prescribed performance control that requires knowledge of initial tracking errors. Some simulation results are provided to demonstrate the feasibility and the effectiveness of the proposed strategy

eess.SY↗

arXiv2024

VisPoison: An Effective Backdoor Attack Framework for Tabular Data Visualization Models

Text-to-visualization (text-to-vis) models for tabular data have become essential tools in the era of big data, enabling users to generate visualizations and make data-driven decisions through natural language queries (NLQs). Despite their growing adoption, the security vulnerabilities of these models remain largely unexplored. To address this gap, we propose VisPoison, a backdoor attack framework that realistically simulates three types of attacks on text-to-vis models via data poisoning: data exposure, misleading visualizations, and denial-of-service (DoS). Specifically, VisPoison introduces two types of stealthy triggers to enable both proactive and passive backdoor activations. Proactive triggers are deliberately inserted by attackers using rare-word patterns to extract sensitive information, whereas passive triggers are unintentionally activated by users through first-word prompts, resulting in visualization errors or DoS failures. To support these triggers, we craft specialized payloads for visualization queries that allow compromised models to function normally on benign inputs while producing malicious outputs in the presence of triggers. Extensive evaluations on both trainable and in-context learning (ICL)-based text-to-vis models show that VisPoison achieves attack success rates exceeding 90\%, exposing serious vulnerabilities. Additionally, existing defense strategies reveal limited effectiveness against VisPoison, underscoring the urgent need for more robust and security-aware text-to-vis systems to safeguard human-data interaction.

cs.CR↗

arXiv2024

XPose: eXplainable Human Pose Estimation

Current approaches in pose estimation primarily concentrate on enhancing model architectures, often overlooking the importance of comprehensively understanding the rationale behind model decisions. In this paper, we propose XPose, a novel framework that incorporates Explainable AI (XAI) principles into pose estimation. This integration aims to elucidate the individual contribution of each keypoint to final prediction, thereby elevating the model's transparency and interpretability. Conventional XAI techniques have predominantly addressed tasks with single-target tasks like classification. Additionally, the application of Shapley value, a common measure in XAI, to pose estimation has been hindered by prohibitive computational demands. To address these challenges, this work introduces an innovative concept called Group Shapley Value (GSV). This approach strategically organizes keypoints into clusters based on their interdependencies. Within these clusters, GSV meticulously calculates Shapley value for keypoints, while for inter-cluster keypoints, it opts for a more holistic group-level valuation. This dual-level computation framework meticulously assesses keypoint contributions to the final outcome, optimizing computational efficiency. Building on the insights into keypoint interactions, we devise a novel data augmentation technique known as Group-based Keypoint Removal (GKR). This method ingeniously removes individual keypoints during training phases, deliberately preserving those with strong mutual connections, thereby refining the model's predictive prowess for non-visible keypoints. The empirical validation of GKR across a spectrum of standard approaches attests to its efficacy. GKR's success demonstrates how using Explainable AI (XAI) can directly enhance pose estimation models.

cs.CV↗

arXiv2024

BoostER: Leveraging Large Language Models for Enhancing Entity Resolution

Entity resolution, which involves identifying and merging records that refer to the same real-world entity, is a crucial task in areas like Web data integration. This importance is underscored by the presence of numerous duplicated and multi-version data resources on the Web. However, achieving high-quality entity resolution typically demands significant effort. The advent of Large Language Models (LLMs) like GPT-4 has demonstrated advanced linguistic capabilities, which can be a new paradigm for this task. In this paper, we propose a demonstration system named BoostER that examines the possibility of leveraging LLMs in the entity resolution process, revealing advantages in both easy deployment and low cost. Our approach optimally selects a set of matching questions and poses them to LLMs for verification, then refines the distribution of entity resolution results with the response of LLMs. This offers promising prospects to achieve a high-quality entity resolution result for real-world applications, especially to individuals or small companies without the need for extensive model training or significant financial investment.

cs.DB↗

arXiv2024

On Leveraging Large Language Models for Enhancing Entity Resolution: A Cost-efficient Approach

Entity resolution, the task of identifying and merging records that refer to the same real-world entity, is crucial in sectors like e-commerce, healthcare, and law enforcement. Large Language Models (LLMs) introduce an innovative approach to this task, capitalizing on their advanced linguistic capabilities and a ``pay-as-you-go'' model that provides significant advantages to those without extensive data science expertise. However, current LLMs are costly due to per-API request billing. Existing methods often either lack quality or become prohibitively expensive at scale. To address these problems, we propose an uncertainty reduction framework using LLMs to improve entity resolution results. We first initialize possible partitions of the entity cluster, refer to the same entity, and define the uncertainty of the result. Then, we reduce the uncertainty by selecting a few valuable matching questions for LLM verification. Upon receiving the answers, we update the probability distribution of the possible partitions. To further reduce costs, we design an efficient algorithm to judiciously select the most valuable matching pairs to query. Additionally, we create error-tolerant techniques to handle LLM mistakes and a dynamic adjustment method to reach truly correct partitions. Experimental results show that our method is efficient and effective, offering promising applications in real-world tasks.

cs.CL↗

arXiv2023

Similarity-driven and Task-driven Models for Diversity of Opinion in Crowdsourcing Markets

The recent boom in crowdsourcing has opened up a new avenue for utilizing human intelligence in the realm of data analysis. This innovative approach provides a powerful means for connecting online workers to tasks that cannot effectively be done solely by machines or conducted by professional experts due to cost constraints. Within the field of social science, four elements are required to construct a sound crowd - Diversity of Opinion, Independence, Decentralization and Aggregation. However, while the other three components have already been investigated and implemented in existing crowdsourcing platforms, 'Diversity of Opinion' has not been functionally enabled yet. From a computational point of view, constructing a wise crowd necessitates quantitatively modeling and taking diversity into account. There are usually two paradigms in a crowdsourcing marketplace for worker selection: building a crowd to wait for tasks to come and selecting workers for a given task. We propose similarity-driven and task-driven models for both paradigms. Also, we develop efficient and effective algorithms for recruiting a limited number of workers with optimal diversity in both models. To validate our solutions, we conduct extensive experiments using both synthetic datasets and real data sets.

stat.AP↗

arXiv2021

HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning

Many real-world data can be represented as heterogeneous graphs with different types of nodes and connections. Heterogeneous graph neural network model aims to embed nodes or subgraphs into low-dimensional vector space for various downstream tasks such as node classification, link prediction, etc. Although several models were proposed recently, they either only aggregate information from the same type of neighbors, or just indiscriminately treat homogeneous and heterogeneous neighbors in the same way. Based on these observations, we propose a new heterogeneous graph neural network model named HMSG to comprehensively capture structural, semantic and attribute information from both homogeneous and heterogeneous neighbors. Specifically, we first decompose the heterogeneous graph into multiple metapath-based homogeneous and heterogeneous subgraphs, and each subgraph associates specific semantic and structural information. Then message aggregation methods are applied to each subgraph independently, so that information can be learned in a more targeted and efficient manner. Through a type-specific attribute transformation, node attributes can also be transferred among different types of nodes. Finally, we fuse information from subgraphs together to get the complete representation. Extensive experiments on several datasets for node classification, node clustering and link prediction tasks show that HMSG achieves the best performance in all evaluation metrics than state-of-the-art baselines.

cs.AI↗

arXiv2019

Game Theoretical Approach to Sequential Hypothesis Test with Byzantine Sensors

In this paper, we consider the problem of sequential binary hypothesis test in adversary environment based on observations from s sensors, with the caveat that a subset of c sensors is compromised by an adversary, whose observations can be manipulated arbitrarily. We choose the asymptotic Average Sample Number (ASN) required to reach a certain level of error probability as the performance metric of the system. The problem is cast as a game between the detector and the adversary, where the detector aims to optimize the system performance while the adversary tries to deteriorate it. We propose a pair of flip attack strategy and voting hypothesis testing rule and prove that they form an equilibrium strategy pair for the game. We further investigate the performance of our proposed detection scheme with unknown number of compromised sensors and corroborate our result with simulation.

eess.SY↗