arXiv subjects

Yiwei Liu

Publications and source records attributed to Yiwei Liu.

At least 37 records · Page 2Linked to original sources

arXiv2025

LogiNumSynth: Synthesizing Joint Logical-Numerical Reasoning Problems for Language Models

Joint logical-numerical reasoning remains a major challenge for language models, yet existing datasets rely on fixed rule sets and offer limited control over task complexity, constraining their generalizability for evaluation and training. We present LogiNumSynth, a flexible natural language problem synthesizer that synthesizes tasks requiring proficiency in joint logical reasoning (e.g., rule-based reasoning) and numerical reasoning (e.g., arithmetic computation). LogiNumSynth supports fine-grained control over reasoning world richness, logical reasoning depth, and the complexity of numerical computations, enabling flexible data synthesis across difficulty levels. We demonstrate three key contributions: (1) Synthesizer -- synthesizing fully controllable joint reasoning tasks over natural language; (2) Evaluation & Process Analysis -- evaluating both process accuracy and answer accuracy; (3) Targeted Training -- using synthesized data to enhance LLMs' reasoning performance. Experiments with multiple LLMs highlight persistent weaknesses in logical-numerical reasoning, showing that LogiNumSynth can serve as both a diagnostic tool and a source of targeted supervision for advancing integrated reasoning skills.

cs.CL↗

arXiv2025

TactfulToM: Do LLMs Have the Theory of Mind Ability to Understand White Lies?

While recent studies explore Large Language Models' (LLMs) performance on Theory of Mind (ToM) reasoning tasks, research on ToM abilities that require more nuanced social context is limited, such as white lies. We introduce TactfulToM, a novel English benchmark designed to evaluate LLMs' ability to understand white lies within real-life conversations and reason about prosocial motivations behind them, particularly when they are used to spare others' feelings and maintain social harmony. Our benchmark is generated through a multi-stage human-in-the-loop pipeline where LLMs expand manually designed seed stories into conversations to maintain the information asymmetry between participants necessary for authentic white lies. We show that TactfulToM is challenging for state-of-the-art models, which perform substantially below humans, revealing shortcomings in their ability to fully comprehend the ToM reasoning that enables true understanding of white lies.

cs.CL↗

arXiv2025

GUI-ReWalk: Massive Data Generation for GUI Agent via Stochastic Exploration and Intent-Aware Reasoning

Graphical User Interface (GUI) Agents, powered by large language and vision-language models, hold promise for enabling end-to-end automation in digital environments. However, their progress is fundamentally constrained by the scarcity of scalable, high-quality trajectory data. Existing data collection strategies either rely on costly and inconsistent manual annotations or on synthetic generation methods that trade off between diversity and meaningful task coverage. To bridge this gap, we present GUI-ReWalk: a reasoning-enhanced, multi-stage framework for synthesizing realistic and diverse GUI trajectories. GUI-ReWalk begins with a stochastic exploration phase that emulates human trial-and-error behaviors, and progressively transitions into a reasoning-guided phase where inferred goals drive coherent and purposeful interactions. Moreover, it supports multi-stride task generation, enabling the construction of long-horizon workflows across multiple applications. By combining randomness for diversity with goal-aware reasoning for structure, GUI-ReWalk produces data that better reflects the intent-aware, adaptive nature of human-computer interaction. We further train Qwen2.5-VL-7B on the GUI-ReWalk dataset and evaluate it across multiple benchmarks, including Screenspot-Pro, OSWorld-G, UI-Vision, AndroidControl, and GUI-Odyssey. Results demonstrate that GUI-ReWalk enables superior coverage of diverse interaction flows, higher trajectory entropy, and more realistic user intent. These findings establish GUI-ReWalk as a scalable and data-efficient framework for advancing GUI agent research and enabling robust real-world automation.

cs.LG↗

arXiv2025

Singularity-free prescribed performance guaranteed control for perturbed system

This paper addresses the prescribed performance control (PPC) challenge for high-order nonlinear systems affected by mismatched disturbances. The research aims to prevent singularity issues arising from error boundary violations during abrupt changes in reference trajectories. We introduce a novel transformation function with infinite-order differentiability at connection points, advancing beyond mere continuous differentiability. Utilizing this transformation function, we develop a comprehensive transformation strategy that ensures: (1) errors remain within prescribed boundaries when reference trajectories are smooth, and (2) errors return to prescribed boundaries within a specified timeframe following abrupt changes in reference trajectories. Additionally, the complexity explosion issue inherent in backstepping design is effectively resolved. Simulation results corroborate the validity of the proposed theoretical advancements.

eess.SY↗

arXiv2025

MetaFold: Language-Guided Multi-Category Garment Folding Framework via Trajectory Generation and Foundation Model

Garment folding is a common yet challenging task in robotic manipulation. The deformability of garments leads to a vast state space and complex dynamics, which complicates precise and fine-grained manipulation. Previous approaches often rely on predefined key points or demonstrations, limiting their generalization across diverse garment categories. This paper presents a framework, MetaFold, that disentangles task planning from action prediction, learning each independently to enhance model generalization. It employs language-guided point cloud trajectory generation for task planning and a low-level foundation model for action prediction. This structure facilitates multi-category learning, enabling the model to adapt flexibly to various user instructions and folding tasks. Experimental results demonstrate the superiority of our proposed framework. Supplementary materials are available on our website: https://meta-fold.github.io/.

cs.RO↗

arXiv2025

Fixed-Time Voltage Regulation for Boost Converters via Unit-Safe Saturating Functions

This paper explores the voltage regulation challenges in boost converter systems, which are critical components in power electronics due to their ability to step up voltage levels efficiently. The proposed control algorithm ensures fixed-time stability, a desirable property that guarantees system stability within a fixed time frame regardless of initial conditions. To tackle the common chattering issues in conventional fixed-time control methods, a novel class of function families is introduced. State observers and adaptive parameters are utilized to manage the uncertainties associated with unknown load resistance. Furthermore, a new disturbance observer is developed using the proposed function family, and its advantages and limitations are illustrated through comparison with existing designs. Finally, both non-real-time and real-time simulations are conducted to validate the effectiveness and deployability of the proposed control algorithm.

eess.SY↗

arXiv2025

Consistent Channel Hopping Algorithms for the Multichannel Rendezvous Problem with Heterogeneous Available Channel Sets

We propose a theoretical framework for consistent channel hopping algorithms to address the multichannel rendezvous problem (MRP) in wireless networks with heterogeneous available channel sets. A channel selection function is called consistent if the selected channel remains unchanged when the available channel set shrinks, provided the selected channel is still available. We show that all consistent channel selection functions are equivalent to the function that always selects the smallest-index channel under appropriate channel relabeling. This leads to a natural representation of a consistent channel hopping algorithm as a sequence of permutations. For the two-user MRP, we characterize rendezvous time slots using a fictitious user and derive tight bounds on the maximum time-to-rendezvous (MTTR) and expected time-to-rendezvous (ETTR). Notably, the ETTR is shown to be the inverse of the Jaccard index when permutations are randomly selected. We also prove that consistent channel hopping algorithms maximize the rendezvous probability. To reduce implementation complexity, we propose the modulo algorithm, which uses modular arithmetic with one-cycle permutations and achieves performance comparable to locality-sensitive hashing (LSH)-based algorithms. The framework is extended to multiple users, with novel strategies such as stick-together, spread-out, and a hybrid method that accelerates rendezvous in both synchronous and asynchronous settings. Simulation results confirm the effectiveness and scalability of the proposed algorithms.

cs.NI↗

arXiv2025

Continuous Multi-Task Pre-training for Malicious URL Detection and Webpage Classification

Malicious URL detection and webpage classification are critical tasks in cybersecurity and information management. In recent years, extensive research has explored using BERT or similar language models to replace traditional machine learning methods for detecting malicious URLs and classifying webpages. While previous studies show promising results, they often apply existing language models to these tasks without accounting for the inherent differences in domain data (e.g., URLs being loosely structured and semantically sparse compared to text), leaving room for performance improvement. Furthermore, current approaches focus on single tasks and have not been tested in multi-task scenarios. To address these challenges, we propose urlBERT, a pre-trained URL encoder leveraging Transformer to encode foundational knowledge from billions of unlabeled URLs. To achieve it, we propose to use 5 unsupervised pretraining tasks to capture multi-level information of URL lexical, syntax, and semantics, and generate contrastive and adversarial representations. Furthermore, to avoid inter-pre-training competition and interference, we proposed a grouped sequential learning method to ensure effective training across multi-tasks. Finally, we leverage a two-stage fine-tuning approach to improve the training stability and efficiency of the task model. To assess the multitasking potential of urlBERT, we fine-tune the task model in both single-task and multi-task modes. The former creates a classification model for a single task, while the latter builds a classification model capable of handling multiple tasks. We evaluate urlBERT on three downstream tasks: phishing URL detection, advertising URL detection, and webpage classification. The results demonstrate that urlBERT outperforms standard pre-trained models, and its multi-task mode is capable of addressing the real-world demands of multitasking.

cs.CR↗

arXiv2025

Fast Multichannel Topology Discovery in Cognitive Radio Networks

In Cognitive Radio Networks (CRNs), secondary users (SUs) must efficiently discover each other across multiple communication channels while avoiding interference from primary users (PUs). Traditional multichannel rendezvous algorithms primarily focus on enabling pairs of SUs to find common channels without explicitly considering the underlying network topology. In this paper, we extend the rendezvous framework to explicitly incorporate network topology, introducing the \emph{multichannel topology discovery problem}. We propose a novel \emph{pseudo-random sweep algorithm with forward replacement}, designed to minimize correlation between consecutive unsuccessful rendezvous attempts, thereby significantly reducing the expected time-to-discovery (ETTD). Additionally, we introduce a \emph{threshold-based stick-together strategy} that dynamically synchronizes user hopping sequences based on partially known information, further enhancing discovery efficiency. Extensive simulation results validate our theoretical analysis, demonstrating that the proposed algorithms substantially outperform conventional (sequential) sweep methods.

cs.NI↗

arXiv2025

PMANet: Malicious URL detection via post-trained language model guided multi-level feature attention network

The proliferation of malicious URLs has made their detection crucial for enhancing network security. While pre-trained language models offer promise, existing methods struggle with domain-specific adaptability, character-level information, and local-global encoding integration. To address these challenges, we propose PMANet, a pre-trained Language Model-Guided multi-level feature attention network. PMANet employs a post-training process with three self-supervised objectives: masked language modeling, noisy language modeling, and domain discrimination, effectively capturing subword and character-level information. It also includes a hierarchical representation module and a dynamic layer-wise attention mechanism for extracting features from low to high levels. Additionally, spatial pyramid pooling integrates local and global features. Experiments on diverse scenarios, including small-scale data, class imbalance, and adversarial attacks, demonstrate PMANet's superiority over state-of-the-art models, achieving a 0.9941 AUC and correctly detecting all 20 malicious URLs in a case study. Code and data are available at https://github.com/Alixyvtte/Malicious-URL-Detection-PMANet.

cs.CR↗

arXiv2025

Verifiable, Efficient and Confidentiality-Preserving Graph Search with Transparency

Graph databases have garnered extensive attention and research due to their ability to manage relationships between entities efficiently. Today, many graph search services have been outsourced to a third-party server to facilitate storage and computational support. Nevertheless, the outsourcing paradigm may invade the privacy of graphs. PeGraph is the latest scheme achieving encrypted search over social graphs to address the privacy leakage, which maintains two data structures XSet and TSet motivated by the OXT technology to support encrypted conjunctive search. However, PeGraph still exhibits limitations inherent to the underlying OXT. It does not provide transparent search capabilities, suffers from expensive computation and result pattern leakages, and it fails to support search over dynamic encrypted graph database and results verification. In this paper, we propose SecGraph to address the first two limitations, which adopts a novel system architecture that leverages an SGX-enabled cloud server to provide users with secure and transparent search services since the secret key protection and computational overhead have been offloaded to the cloud server. Besides, we design an LDCF-encoded XSet based on the Logarithmic Dynamic Cuckoo Filter to facilitate efficient plaintext computation in trusted memory, effectively mitigating the risks of result pattern leakage and performance degradation due to exceeding the limited trusted memory capacity. Finally, we design a new dynamic version of TSet named Twin-TSet to enable conjunctive search over dynamic encrypted graph database. In order to support verifiable search, we further propose VSecGraph, which utilizes a procedure-oriented verification method to verify all data structures loaded into the trusted memory, thus bypassing the computational overhead associated with the client's local verification.

cs.CR↗

arXiv2025

Some rigidity results related to the Obata type equation

Let $(Ω^{n+1},g)$ be an $(n + 1)$-dimensional smooth complete connected Riemannian manifold with compact boundary $\partialΩ=Σ$ and $f$ a smooth function on $Ω$ which satisfies the Obata type equation $\nabla^2 f -fg =0$ with Robin boundary condition $f_ν = cf$, where $c=\cothθ>1$. In this paper, we provide some rigidity results based on the warped product structure of $Ω$ determined by the equation $\nabla^2 f -fg =0$ and appropriate curvature assumptions. We also apply a similar method to the Obata type equation $\nabla^2 f +fg =0$ and get a rigidity result on the standard sphere $\mathbb{S}^{n+1}$.

math.DG↗

arXiv2025

Ethereum Fraud Detection via Joint Transaction Language Model and Graph Representation Learning

Ethereum faces growing fraud threats. Current fraud detection methods, whether employing graph neural networks or sequence models, fail to consider the semantic information and similarity patterns within transactions. Moreover, these approaches do not leverage the potential synergistic benefits of combining both types of models. To address these challenges, we propose TLMG4Eth that combines a transaction language model with graph-based methods to capture semantic, similarity, and structural features of transaction data in Ethereum. We first propose a transaction language model that converts numerical transaction data into meaningful transaction sentences, enabling the model to learn explicit transaction semantics. Then, we propose a transaction attribute similarity graph to learn transaction similarity information, enabling us to capture intuitive insights into transaction anomalies. Additionally, we construct an account interaction graph to capture the structural information of the account transaction network. We employ a deep multi-head attention network to fuse transaction semantic and similarity embeddings, and ultimately propose a joint training approach for the multi-head attention network and the account interaction graph to obtain the synergistic benefits of both.

cs.CR↗

arXiv2024

The Role of Transformer Models in Advancing Blockchain Technology: A Systematic Survey

As blockchain technology rapidly evolves, the demand for enhanced efficiency, security, and scalability grows.Transformer models, as powerful deep learning architectures,have shown unprecedented potential in addressing various blockchain challenges. However, a systematic review of Transformer applications in blockchain is lacking. This paper aims to fill this research gap by surveying over 200 relevant papers, comprehensively reviewing practical cases and research progress of Transformers in blockchain applications. Our survey covers key areas including anomaly detection, smart contract security analysis, cryptocurrency prediction and trend analysis, and code summary generation. To clearly articulate the advancements of Transformers across various blockchain domains, we adopt a domain-oriented classification system, organizing and introducing representative methods based on major challenges in current blockchain research. For each research domain,we first introduce its background and objectives, then review previous representative methods and analyze their limitations,and finally introduce the advancements brought by Transformer models. Furthermore, we explore the challenges of utilizing Transformer, such as data privacy, model complexity, and real-time processing requirements. Finally, this article proposes future research directions, emphasizing the importance of exploring the Transformer architecture in depth to adapt it to specific blockchain applications, and discusses its potential role in promoting the development of blockchain technology. This review aims to provide new perspectives and a research foundation for the integrated development of blockchain technology and machine learning, supporting further innovation and application expansion of blockchain technology.

cs.LG↗

arXiv2023

Ultra-conformable Liquid Metal Particle Monolayer on Air/water Interface for Substrate-free E-tattoo

Gallium-based liquid metal is getting increased attention in conformal flexible electronics for its high electrical conductivity, intrinsic deformability and biocompatibility. A series of flexible devices are developed based on the micro-particles of liquid metal. But it is still challenging to fabricate conformal liquid metal film with a large area and high uniformity. Interfacial self-assembly is a competitive candidate method. Traditional interfacial self-assembly methods have difficulties assembling liquid metal particles because the floating state of the high-density microparticles could be easily disturbed by gravity. Here, we realized the multi-size universal self-assembly (MUS) for liquid metal particles with various diameters (0~500μm). By introducing a simple z-axis undisturbed interfacial material releasing strategy, the interference of gravitational energy on the stability of floating particles is avoided. Benefits from this, the ultra-conformable monolayer film, with large area (>100 cm2) and high floating yield (50%~90%), can be fabricated by liquid metal particles. Furthermore, the monolayer can be conformally transferred to any interesting complex surface such as human skin and plant leaf, to fabricate substrate-free flexible devices. Without interference from the mechanical response of traditional substrate, the liquid metal e-tattoo is more user-friendly and can realize feel-less continuous monitoring.

physics.app-ph↗

arXiv2023

MSDC: Exploiting Multi-State Power Consumption in Non-intrusive Load Monitoring based on A Dual-CNN Model

Non-intrusive load monitoring (NILM) aims to decompose aggregated electrical usage signal into appliance-specific power consumption and it amounts to a classical example of blind source separation tasks. Leveraging recent progress on deep learning techniques, we design a new neural NILM model Multi-State Dual CNN (MSDC). Different from previous models, MSDC explicitly extracts information about the appliance's multiple states and state transitions, which in turn regulates the prediction of signals for appliances. More specifically, we employ a dual-CNN architecture: one CNN for outputting state distributions and the other for predicting the power of each state. A new technique is invented that utilizes conditional random fields (CRF) to capture state transitions. Experiments on two real-world datasets REDD and UK-DALE demonstrate that our model significantly outperform state-of-the-art models while having good generalization capacity, achieving 6%-10% MAE gain and 33%-51% SAE gain to unseen appliances.

cs.LG↗

arXiv2022

GraphEye: A Novel Solution for Detecting Vulnerable Functions Based on Graph Attention Network

With the continuous extension of the Industrial Internet, cyber incidents caused by software vulnerabilities have been increasing in recent years. However, software vulnerabilities detection is still heavily relying on code review done by experts, and how to automatedly detect software vulnerabilities is an open problem so far. In this paper, we propose a novel solution named GraphEye to identify whether a function of C/C++ code has vulnerabilities, which can greatly alleviate the burden of code auditors. GraphEye is originated from the observation that the code property graph of a non-vulnerable function naturally differs from the code property graph of a vulnerable function with the same functionality. Hence, detecting vulnerable functions is attributed to the graph classification problem.GraphEye is comprised of VecCPG and GcGAT. VecCPG is a vectorization for the code property graph, which is proposed to characterize the key syntax and semantic features of the corresponding source code. GcGAT is a deep learning model based on the graph attention graph, which is proposed to solve the graph classification problem according to VecCPG. Finally, GraphEye is verified by the SARD Stack-based Buffer Overflow, Divide-Zero, Null Pointer Deference, Buffer Error, and Resource Error datasets, the corresponding F1 scores are 95.6%, 95.6%,96.1%,92.6%, and 96.1% respectively, which validate the effectiveness of the proposed solution.

cs.CR↗

arXiv2021

Adaptive Remote Sensing Image Attribute Learning for Active Object Detection

In recent years, deep learning methods bring incredible progress to the field of object detection. However, in the field of remote sensing image processing, existing methods neglect the relationship between imaging configuration and detection performance, and do not take into account the importance of detection performance feedback for improving image quality. Therefore, detection performance is limited by the passive nature of the conventional object detection framework. In order to solve the above limitations, this paper takes adaptive brightness adjustment and scale adjustment as examples, and proposes an active object detection method based on deep reinforcement learning. The goal of adaptive image attribute learning is to maximize the detection performance. With the help of active object detection and image attribute adjustment strategies, low-quality images can be converted into high-quality images, and the overall performance is improved without retraining the detector.

cs.CV↗