arXiv subjects

Yuheng Wang

Publications and source records attributed to Yuheng Wang.

At least 37 records · Page 2Linked to original sources

arXiv2025

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent

With the raid evolution of large language models and multimodal models, the mobile-agent landscape has proliferated without converging on the fundamental challenges. This paper identifies four core problems that should be solved for mobile agents to deliver practical, scalable impact: (1) generalization across tasks, APPs, and devices; (2) accuracy, specifically precise on-screen interaction and click targeting; (3) long-horizon capability for sustained, multi-step goals; and (4) efficiency, specifically high-performance runtime on resource-constrained devices. We present AppCopilot, a multimodal, multi-agent, general-purpose mobile agent that operates across applications. AppCopilot operationalizes this position through an end-to-end pipeline spanning data collection, training, finetuning, efficient inference, and PC/mobile application. At the model layer, it integrates multimodal foundation models with robust Chinese-English support. At the reasoning and control layer, it combines chain-of-thought reasoning, hierarchical task planning and decomposition, and multi-agent collaboration. At the execution layer, it enables experiential adaptation, voice interaction, function calling, cross-APP and cross-device orchestration, and comprehensive mobile APP support. The system design incorporates profiling-driven optimization for latency and memory across heterogeneous hardware. Empirically, AppCopilot achieves significant improvements on four dimensions: stronger generalization, higher precision of on screen actions, more reliable long horizon task completion, and faster, more resource efficient runtime. By articulating a cohesive position and a reference architecture that closes the loop from data collection, training to finetuning and efficient inference, this paper offers a concrete roadmap for general purpose mobile agent and provides actionable guidance.

cs.AI↗

arXiv2025

Thunderdome: Timelock-Free Rationally-Secure Virtual Channels

Payment channel networks (PCNs) offer a promising solution to address the limited transaction throughput of deployed blockchains. However, several attacks have recently been proposed that stress the vulnerability of PCNs to timelock and censoring attacks. To address such attacks, we introduce Thunderdome, the first timelock-free PCN. Instead, Thunderdome leverages the design rationale of virtual channels to extend a timelock-free payment channel primitive, thereby enabling multi-hop transactions without timelocks. Previous works either utilize timelocks or do not accommodate transactions between parties that do not share a channel. At its core, Thunderdome relies on a committee of non-trusted watchtowers, known as wardens, who ensure that no honest party loses funds, even when offline, during the channel closure process. We introduce tailored incentive mechanisms to ensure that all participants follow the protocol's correct execution. Besides a traditional security proof that assumes an honest majority of the committee, we conduct a formal game-theoretic analysis to demonstrate the security of Thunderdome when all participants, including wardens, act rationally. We implement a proof of concept of Thunderdome on Ethereum to validate its feasibility and evaluate its costs. Our evaluation shows that deploying Thunderdome, including opening the underlying payment channel, costs approximately \$15 (0.0089 ETH), while the worst-case cost for closing a channel is about \$7 (0.004 ETH).

cs.CR↗

arXiv2025

Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the 7-Point Checklist

The 7-point checklist (7PCL) is a widely used diagnostic tool in dermoscopy for identifying malignant melanoma by assigning point values to seven specific attributes. However, the traditional 7PCL is limited to distinguishing between malignant melanoma and melanocytic Nevi, and falls short in scenarios where multiple skin diseases with appearances similar to melanoma coexist. To address this limitation, we propose a novel diagnostic framework that integrates a clinical knowledge-based topological graph (CKTG) with a gradient diagnostic strategy featuring a data-driven weighting system (GD-DDW). The CKTG captures both the internal and external relationships among the 7PCL attributes, while the GD-DDW emulates dermatologists' diagnostic processes, prioritizing visual observation before making predictions. Additionally, we introduce a multimodal feature extraction approach leveraging a dual-attention mechanism to enhance feature extraction through cross-modal interaction and unimodal collaboration. This method incorporates meta-information to uncover interactions between clinical data and image features, ensuring more accurate and robust predictions. Our approach, evaluated on the EDRA dataset, achieved an average AUC of 88.6%, demonstrating superior performance in melanoma detection and feature prediction. This integrated system provides data-driven benchmarks for clinicians, significantly enhancing the precision of melanoma diagnosis.

cs.CV↗

arXiv2025

MemeCMD: An Automatically Generated Chinese Multi-turn Dialogue Dataset with Contextually Retrieved Memes

Memes are widely used in online social interactions, providing vivid, intuitive, and often humorous means to express intentions and emotions. Existing dialogue datasets are predominantly limited to either manually annotated or pure-text conversations, lacking the expressiveness and contextual nuance that multimodal interactions provide.To address these challenges, we introduce MemeCMD, an automatically generated Chinese Multi-turn Dialogue dataset with contextually retrieved memes. Our dataset combines a large-scale, MLLM-annotated meme library with dialogues auto-generated by dual agents across diverse scenarios. We introduce a retrieval framework and adaptive threshold to ensure contextually relevant, naturally spaced meme usage. Experiments demonstrate the effectiveness of our approach in generating contextually appropriate and diverse meme-incorporated dialogues, offering a scalable and privacy-preserving resource for advancing multimodal conversational AI.

cs.CL↗

arXiv2025

MAC-Gaze: Motion-Aware Continual Calibration for Mobile Gaze Tracking

Mobile gaze tracking faces a fundamental challenge: maintaining accuracy as users naturally change their postures and device orientations. Traditional calibration approaches, like one-off, fail to adapt to these dynamic conditions, leading to degraded performance over time. We present MAC-Gaze, a Motion-Aware continual Calibration approach that leverages smartphone Inertial measurement unit (IMU) sensors and continual learning techniques to automatically detect changes in user motion states and update the gaze tracking model accordingly. Our system integrates a pre-trained visual gaze estimator and an IMU-based activity recognition model with a clustering-based hybrid decision-making mechanism that triggers recalibration when motion patterns deviate significantly from previously encountered states. To enable accumulative learning of new motion conditions while mitigating catastrophic forgetting, we employ replay-based continual learning, allowing the model to maintain performance across previously encountered motion conditions. We evaluate our system through extensive experiments on the publicly available RGBDGaze dataset and our own 10-hour multimodal MotionGaze dataset (481K+ images, 800K+ IMU readings), encompassing a wide range of postures under various motion conditions including sitting, standing, lying, and walking. Results demonstrate that our method reduces gaze estimation error by 19.9% on RGBDGaze (from 1.73 cm to 1.41 cm) and by 31.7% on MotionGaze (from 2.81 cm to 1.92 cm) compared to traditional calibration approaches. Our framework provides a robust solution for maintaining gaze estimation accuracy in mobile scenarios.

cs.HC↗

arXiv2025

FormFactory: An Interactive Benchmarking Suite for Multimodal Form-Filling Agents

Online form filling is a common yet labor-intensive task involving extensive keyboard and mouse interactions. Despite the long-standing vision of automating this process with "one click", existing tools remain largely rule-based and lack generalizable, generative capabilities. Recent advances in Multimodal Large Language Models (MLLMs) have enabled promising agents for GUI-related tasks in general-purpose scenarios. However, they struggle with the unique challenges of form filling, such as flexible layouts and the difficulty of aligning textual instructions with on-screen fields. To bridge this gap, we formally define the form-filling task and propose FormFactory, an interactive benchmarking suite comprising a web-based interface, backend evaluation module, and carefully constructed dataset. Our benchmark covers diverse real-world scenarios, incorporates various field formats, and simulates high-fidelity form interactions. We conduct a comprehensive evaluation of state-of-the-art MLLMs and observe that no model surpasses 5% accuracy, underscoring the inherent difficulty of the task. These findings also reveal significant limitations in current models' visual layout reasoning and field-value alignment abilities. We hope our benchmark can serve as a stepping stone for further research into robust, practical form-filling agents.

cs.CL↗

arXiv2025

Robust and Scalable Renaming with Subquadratic Bits

In the renaming problem, a set of $n$ nodes, each with a unique identity from a large namespace $[N]$, needs to obtain new unique identities in a smaller namespace $[M]$. A renaming algorithm is strong if $M=n$. Renaming is a classical problem in distributed computing with a range of applications, and there exist many time-efficient solutions for fault-tolerant renaming in synchronous message-passing systems. However, all previous algorithms send $Ω(n^2)$ messages, and many of them also send large messages each containing $Ω(n)$ bits. Moreover, most algorithms' performance do not scale with the actual number of failures. These limitations restrict their practical performance. We develop two new strong renaming algorithms, one tolerates up to $n-1$ crash failures, and the other tolerates up to $(1/3-ε_0)n$ Byzantine failures for an arbitrarily small constant $ε_0>0$. The crash-resilient algorithm is always correct and always finishes within $O(\log{n})$ rounds. It sends $\tilde{O}((f+1)\cdot n)$ messages with high probability, where $f$ is the actual number of crashes. This implies that it sends subquadratic messages as long as $f=o(n/\log{n})$. The Byzantine-resilient algorithm trades time for communication: it finishes within $\tilde{O}(\max\{f,1\})$ rounds and sends only $\tilde{O}(f+n)$ messages, with high probability. Here, $f$ is the actual number of Byzantine nodes. To obtain such strong guarantees, the Byzantine-resilient algorithm leverages shared randomness and message authentication. Both algorithms only send messages of size $O(\log{N})$ bits. Therefore, our crash-resilient algorithm incurs $o(n^2)$ communication cost as long as $f=o(n/(\log{n}\log{N}))$; and our Byzantine resilient algorithm incurs almost-linear communication cost. By deriving a lower bound, we conclude that our algorithms achieve near-optimal communication cost in many cases.

cs.DC↗

arXiv2024

Knowledge Authoring with Factual English, Rules, and Actions

Knowledge representation and reasoning systems represent knowledge as collections of facts and rules. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. Some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. Besides the CNL restrictions, KALM has limitations in terms of the types of knowledge it can represent. To address these issues, we propose an extension of KALM called KALM for Factual Language (KALMF). KALMF uses a neural parser for natural language, MS, to parse what we call factual English sentences, which require little grammar training to use. Building upon KALMF, we propose KALM for Rules and Actions (KALMR), to represent and reason with rules and actions. Furthermore, we identify the reasons behind the slow speed of KALM and make optimizations to address this issue. Our evaluation using multiple benchmarks shows that our approaches achieve a high level of correctness on fact and query authoring (95%) and on rule authoring (100%). When used for authoring and reasoning with actions, our approach achieves more than 99.3% correctness, demonstrating its effectiveness in enabling more sophisticated knowledge representation and reasoning. We also illustrate the logical reasoning capabilities of our approach by drawing attention to the problems faced by the famous AI, ChatGPT. Finally, the evaluation of the newly proposed speed optimization points not only to a 68% runtime improvement but also yields better accuracy of the overall system.

cs.AI↗

arXiv2024

Approximate Maximum Likelihood Inference for Acoustic Spatial Capture-Recapture with Unknown Identities, Using Monte Carlo Expectation Maximization

Acoustic spatial capture-recapture (ASCR) surveys with an array of synchronized acoustic detectors can be an effective way of estimating animal density or call density. However, constructing the capture histories required for ASCR analysis is challenging, as recognizing which detections at different detectors are of which calls is not a trivial task. Because calls from different distances take different times to arrive at detectors, the order in which calls are detected is not necessarily the same as the order in which they are made, and without knowing which detections are of the same call, we do not know how many different calls are detected. We propose a Monte Carlo expectation-maximization (MCEM) estimation method to resolve this unknown call identity problem. To implement the MCEM method in this context, we sample the latent variables from a complete-data likelihood model in the expectation step and use a semi-complete-data likelihood or conditional likelihood in the maximization step. We use a parametric bootstrap to obtain confidence intervals. When we apply our method to a survey of moss frogs, it gives an estimate within 15% of the estimate obtained using data with call capture histories constructed by experts, and unlike this latter estimate, our confidence interval incorporates the uncertainty about call identities. Simulations show it to have a low bias (6%) and coverage probabilities close to the nominal 95% value.

stat.ME↗

arXiv2024

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

Neural style transfer (NST) generates new images by combining the style of one image with the content of another. However, unauthorized NST can exploit artwork, raising concerns about artists' rights and motivating the development of proactive protection methods. We propose Locally Adaptive Adversarial Color Attack (LAACA), empowering artists to protect their artwork from unauthorized style transfer by processing before public release. By delving into the intricacies of human visual perception and the role of different frequency components, our method strategically introduces frequency-adaptive perturbations in the image. These perturbations significantly degrade the generation quality of NST while maintaining an acceptable level of visual change in the original image, ensuring that potential infringers are discouraged from using the protected artworks, because of its bad NST generation quality. Additionally, existing metrics often overlook the importance of color fidelity in evaluating color-mattered tasks, such as the quality of NST-generated images, which is crucial in the context of artistic works. To comprehensively assess the color-mattered tasks, we propose the Adversarial Color Distance Metric (ACDM), designed to quantify the color difference of images pre- and post-manipulations. Experimental results confirm that attacking NST using LAACA results in visually inferior style transfer, and the ACDM can efficiently measure color-mattered tasks. By providing artists with a tool to safeguard their intellectual property, our work relieves the socio-technical challenges posed by the misuse of NST in the art community.

cs.CV↗

arXiv2023

Towards Automated Animal Density Estimation with Acoustic Spatial Capture-Recapture

Passive acoustic monitoring can be an effective way of monitoring wildlife populations that are acoustically active but difficult to survey visually. Digital recorders allow surveyors to gather large volumes of data at low cost, but identifying target species vocalisations in these data is non-trivial. Machine learning (ML) methods are often used to do the identification. They can process large volumes of data quickly, but they do not detect all vocalisations and they do generate some false positives (vocalisations that are not from the target species). Existing wildlife abundance survey methods have been designed specifically to deal with the first of these mistakes, but current methods of dealing with false positives are not well-developed. They do not take account of features of individual vocalisations, some of which are more likely to be false positives than others. We propose three methods for acoustic spatial capture-recapture inference that integrate individual-level measures of confidence from ML vocalisation identification into the likelihood and hence integrate ML uncertainty into inference. The methods include a mixture model in which species identity is a latent variable. We test the methods by simulation and find that in a scenario based on acoustic data from Hainan gibbons, in which ignoring false positives results in 17% positive bias, our methods give negligible bias and coverage probabilities that are close to the nominal 95% level.

cs.SD↗

arXiv2023

Knowledge Authoring for Rules and Actions

Knowledge representation and reasoning (KRR) systems describe and reason with complex concepts and relations in the form of facts and rules. Unfortunately, wide deployment of KRR systems runs into the problem that domain experts have great difficulty constructing correct logical representations of their domain knowledge. Knowledge engineers can help with this construction process, but there is a deficit of such specialists. The earlier Knowledge Authoring Logic Machine (KALM) based on Controlled Natural Language (CNL) was shown to have very high accuracy for authoring facts and questions. More recently, KALMFL, a successor of KALM, replaced CNL with factual English, which is much less restrictive and requires very little training from users. However, KALMFL has limitations in representing certain types of knowledge, such as authoring rules for multi-step reasoning or understanding actions with timestamps. To address these limitations, we propose KALMRA to enable authoring of rules and actions. Our evaluation using the UTI guidelines benchmark shows that KALMRA achieves a high level of correctness (100%) on rule authoring. When used for authoring and reasoning with actions, KALMRA achieves more than 99.3% correctness on the bAbI benchmark, demonstrating its effectiveness in more sophisticated KRR jobs. Finally, we illustrate the logical reasoning capabilities of KALMRA by drawing attention to the problems faced by the recently made famous AI, ChatGPT.

cs.CL↗

arXiv2023

DynamicRead: Exploring Robust Gaze Interaction Methods for Reading on Handheld Mobile Devices under Dynamic Conditions

Enabling gaze interaction in real-time on handheld mobile devices has attracted significant attention in recent years. An increasing number of research projects have focused on sophisticated appearance-based deep learning models to enhance the precision of gaze estimation on smartphones. This inspires important research questions, including how the gaze can be used in a real-time application, and what type of gaze interaction methods are preferable under dynamic conditions in terms of both user acceptance and delivering reliable performance. To address these questions, we design four types of gaze scrolling techniques: three explicit technique based on Gaze Gesture, Dwell time, and Pursuit; and one implicit technique based on reading speed to support touch-free, page-scrolling on a reading application. We conduct a 20-participant user study under both sitting and walking settings and our results reveal that Gaze Gesture and Dwell time-based interfaces are more robust while walking and Gaze Gesture has achieved consistently good scores on usability while not causing high cognitive workload.

cs.HC↗

arXiv2022

Knowledge Authoring with Factual English

Knowledge representation and reasoning (KRR) systems represent knowledge as collections of facts and rules. Like databases, KRR systems contain information about domains of human activities like industrial enterprises, science, and business. KRRs can represent complex concepts and relations, and they can query and manipulate information in sophisticated ways. Unfortunately, the KRR technology has been hindered by the fact that specifying the requisite knowledge requires skills that most domain experts do not have, and professional knowledge engineers are hard to find. One solution could be to extract knowledge from English text, and a number of works have attempted to do so (OpenSesame, Google's Sling, etc.). Unfortunately, at present, extraction of logical facts from unrestricted natural language is still too inaccurate to be used for reasoning, while restricting the grammar of the language (so-called controlled natural language, or CNL) is hard for the users to learn and use. Nevertheless, some recent CNL-based approaches, such as the Knowledge Authoring Logic Machine (KALM), have shown to have very high accuracy compared to others, and a natural question is to what extent the CNL restrictions can be lifted. In this paper, we address this issue by transplanting the KALM framework to a neural natural language parser, mStanza. Here we limit our attention to authoring facts and queries and therefore our focus is what we call factual English statements. Authoring other types of knowledge, such as rules, will be considered in our followup work. As it turns out, neural network based parsers have problems of their own and the mistakes they make range from part-of-speech tagging to lemmatization to dependency errors. We present a number of techniques for combating these problems and test the new system, KALMFL (i.e., KALM for factual language), on a number of benchmarks, which show KALMFL achieves correctness in excess of 95%.

cs.LO↗

arXiv2022

Risk-averse autonomous systems: A brief history and recent developments from the perspective of optimal control

We present an historical overview about the connections between the analysis of risk and the control of autonomous systems. We offer two main contributions. Our first contribution is to propose three overlapping paradigms to classify the vast body of literature: the worst-case, risk-neutral, and risk-averse paradigms. We consider an appropriate assessment for the risk of an autonomous system to depend on the application at hand. In contrast, it is typical to assess risk using an expectation, variance, or probability alone. Our second contribution is to unify the concepts of risk and autonomous systems. We achieve this by connecting approaches for quantifying and optimizing the risk that arises from a system's behaviour across academic fields. The survey is highly multidisciplinary. We include research from the communities of reinforcement learning, stochastic and robust control theory, operations research, and formal verification. We describe both model-based and model-free methods, with emphasis on the former. Lastly, we highlight fruitful areas for further research. A key direction is to blend risk-averse model-based and model-free methods to enhance the real-time adaptive capabilities of systems to improve human and environmental welfare.

cs.AI↗

arXiv2022

Toward Scalable Risk Analysis for Stochastic Systems Using Extreme Value Theory

We aim to analyze the behaviour of a finite-time stochastic system, whose model is not available, in the context of more rare and harmful outcomes. Standard estimators are not effective in making predictions about such outcomes due to their rarity. Instead, we use Extreme Value Theory (EVT), the theory of the long-term behaviour of normalized maxima of random variables. We quantify risk using the upper-semideviation $ρ(Y) = E(\max\{Y - μ,0\})$ of an integrable random variable $Y$ with mean $μ= E(Y)$. $ρ(Y)$ is the risk-aware part of the common mean-upper-semideviation functional $μ+ λρ(Y)$ with $λ\in [0,1]$. To assess more rare and harmful outcomes, we propose an EVT-based estimator for $ρ(Y)$ in a given fraction of the worst cases. We show that our estimator enjoys a closed-form representation in terms of the popular conditional value-at-risk functional. In experiments, we illustrate the extrapolation power of our estimator using a small number of i.i.d. samples ($<$50). Our approach is useful for estimating the risk of finite-time systems when models are inaccessible and data collection is expensive. The numerical complexity does not grow with the size of the state space.

stat.ME↗

arXiv2022

SSD-KD: A Self-supervised Diverse Knowledge Distillation Method for Lightweight Skin Lesion Classification Using Dermoscopic Images

Skin cancer is one of the most common types of malignancy, affecting a large population and causing a heavy economic burden worldwide. Over the last few years, computer-aided diagnosis has been rapidly developed and make great progress in healthcare and medical practices due to the advances in artificial intelligence. However, most studies in skin cancer detection keep pursuing high prediction accuracies without considering the limitation of computing resources on portable devices. In this case, knowledge distillation (KD) has been proven as an efficient tool to help improve the adaptability of lightweight models under limited resources, meanwhile keeping a high-level representation capability. To bridge the gap, this study specifically proposes a novel method, termed SSD-KD, that unifies diverse knowledge into a generic KD framework for skin diseases classification. Our method models an intra-instance relational feature representation and integrates it with existing KD research. A dual relational knowledge distillation architecture is self-supervisedly trained while the weighted softened outputs are also exploited to enable the student model to capture richer knowledge from the teacher model. To demonstrate the effectiveness of our method, we conduct experiments on ISIC 2019, a large-scale open-accessed benchmark of skin diseases dermoscopic images. Experiments show that our distilled lightweight model can achieve an accuracy as high as 85% for the classification tasks of 8 different skin diseases with minimal parameters and computing requirements. Ablation studies confirm the effectiveness of our intra- and inter-instance relational knowledge integration strategy. Compared with state-of-the-art knowledge distillation techniques, the proposed method demonstrates improved performances for multi-diseases classification on the large-scale dermoscopy database.

cs.CV↗

arXiv2021

Loss Comparison of Electric Vehicle Fuel Cell Integration Methods

This study analyzes and compares the drivetrain losses of two methods of fuel cell integration in electric vehicle drivetrains. The first is a conventional (boosted) two-stage system while the second is a dual inverter based solution. Each source of drivetrain losses is described by mathematical equations and the impact of higher order harmonics are observed through circuit model simulation. The dual inverter system achieves an overall energy efficiency improvement of 5.27% and 10.13% for highway and urban driving compared to the conventional method. The use of lower voltage rated power modules and lower switching frequency in the dual inverter system has significantly reduced the switching losses and improved the driving efficiency.

eess.SY↗