arXiv subjects

Xinyuan Wu

Publications and source records attributed to Xinyuan Wu.

At least 19 recordsLinked to original sources

arXiv2026

Operational digital twin clinics enable task-based evaluation of embodied AI

Embodied artificial intelligence (AI) must be tested in the clinical environments where it will operate, but building realistic, robot-testable settings is costly and difficult to scale. Here we show that routine clinic images can be transformed into operational digital twins for task-based evaluation of embodied AI. Using 39 ophthalmic clinic scenes, we converted single photographs into editable, simulator-ready environments and assessed reconstruction quality, room-scale geometry, mesh grounding, multi-robot feasibility, perturbation sensitivity and closed-loop policy performance. The reconstructed scenes preserved workspace structure, while local editing enabled controlled device reconfiguration. Device meshes, collision proxies and semantic anchors converted visual reconstructions into contact-aware simulation scenes. Across three robot embodiments, shared task targets showed different patterns of reachability and contact feasibility. Small device translations and rotations produced task-specific changes in contact margins that were not captured by visual similarity alone. Digital-twin trajectories also supported local policy learning and closed-loop evaluation. These findings establish operational validity as a key principle for clinical digital twins and provide an intermediate layer between offline development and physical deployment of embodied AI in healthcare.

cs.RO↗

arXiv2026

EyeWorld: A Generative World Model of Ocular State and Dynamics

Ophthalmic decision-making depends on subtle lesion-scale cues interpreted across multimodal imaging and over time, yet most medical foundation models remain static and degrade under modality and acquisition shifts. Here we introduce EyeWorld, a generative world model that conceptualizes the eye as a partially observed dynamical system grounded in clinical imaging. EyeWorld learns an observation-stable latent ocular state shared across modalities, unifying fine-grained parsing, structure-preserving cross-modality translation and quality-robust enhancement within a single framework. Longitudinal supervision further enables time-conditioned state transitions, supporting forecasting of clinically meaningful progression while preserving stable anatomy. By moving from static representation learning to explicit dynamical modeling, EyeWorld provides a unified approach to robust multimodal interpretation and prognosis-oriented simulation in medicine.

cs.CV↗

arXiv2026

EyeAgent: An Agentic AI System for Multimodal Clinical Decision Support in Ophthalmology

Artificial intelligence has shown promise in medical imaging, yet most existing systems lack flexibility, interpretability, and adaptability - challenges especially pronounced in ophthalmology, where diverse imaging modalities are essential. We present EyeAgent, the first agentic AI framework for comprehensive and interpretable clinical decision support in ophthalmology. Using a large language model (DeepSeek-V3) as its central reasoning engine, EyeAgent interprets user queries and dynamically orchestrates 53 validated ophthalmic tools across 23 imaging modalities for diverse tasks including classification, segmentation, detection, image/report generation, and quantitative analysis. Stepwise ablation analysis demonstrated a progressive improvement in diagnostic accuracy, rising from a baseline of 69.71% (using only 5 general tools) to 80.79% when the full suite of 53 specialized tools was integrated. In an expert rating study on 200 real-world clinical cases, EyeAgent achieved 93.7% tool selection accuracy and received expert ratings of more than 88% across accuracy, completeness, safety, reasoning, and interpretability. In human-AI collaboration, EyeAgent matched or exceeded the performance of senior ophthalmologists and, when used as an assistant, improved overall diagnostic accuracy by 18.51% and report quality scores by 19%, with the greatest benefit observed among junior ophthalmologists. These findings establish EyeAgent as a scalable and trustworthy AI framework for ophthalmology and provide a blueprint for modular, multimodal, and clinically aligned next-generation AI systems.

cs.HC↗

arXiv2025

ChatMyopia: An AI Agent for Pre-consultation Education in Primary Eye Care Settings

Large language models (LLMs) show promise for tailored healthcare communication but face challenges in interpretability and multi-task integration particularly for domain-specific needs like myopia, and their real-world effectiveness as patient education tools has yet to be demonstrated. Here, we introduce ChatMyopia, an LLM-based AI agent designed to address text and image-based inquiries related to myopia. To achieve this, ChatMyopia integrates an image classification tool and a retrieval-augmented knowledge base built from literature, expert consensus, and clinical guidelines. Myopic maculopathy grading task, single question examination and human evaluations validated its ability to deliver personalized, accurate, and safe responses to myopia-related inquiries with high scalability and interpretability. In a randomized controlled trial (n=70, NCT06607822), ChatMyopia significantly improved patient satisfaction compared to traditional leaflets, enhancing patient education in accuracy, empathy, disease awareness, and patient-eyecare practitioner communication. These findings highlight ChatMyopia's potential as a valuable supplement to enhance patient education and improve satisfaction with medical services in primary eye care settings.

cs.HC↗

arXiv2025

The existence of explicit symplectic integrators for general nonseparable Hamiltonian systems

The existence of explicit symplectic integrators for general nonseparable Hamiltonian systems is an open and important problem in both numerical analysis and computing in science and engineering, as explicit integrators are usually more efficient than the implicit integrators of the same order of accuracy. Up to now, all responses to this problem are negative. That is, there exist explicit symplectic integrators only for some special nonseparable Hamiltonian systems, whereas the universal design involving explicit symplectic integrators for general nonseparable Hamiltonian systems has not yet been studied sufficiently. In this paper, we present a constructive proof for the existence of explicit symplectic integrators for general nonseparable Hamiltonian systems via finding explicit symplectic mappings under which the special submanifold of the extended phase space is invariant. It turns out that the proposed explicit integrators are symplectic in both the extended phase space and the original phase space. Moreover, on the basis of the global modified Hamiltonians of the proposed integrators, the backward error analysis is made via a parameter relaxation and restriction technique to show the linear growth of global errors and the near-preservation of first integrals. In particular, the effective estimated time interval is nearly the same as classical implicit symplectic integrators when applied to (near-) integrable Hamiltonian systems. Numerical experiments with a completely integrable nonseparable Hamiltonian and a nonintegrable nonseparable Hamiltonian illustrate the good long-term behavior and high efficiency of the explicit symplectic integrators proposed and analyzed in this paper.

math.NA↗

arXiv2024

FFA Sora, video generation as fundus fluorescein angiography simulator

Fundus fluorescein angiography (FFA) is critical for diagnosing retinal vascular diseases, but beginners often struggle with image interpretation. This study develops FFA Sora, a text-to-video model that converts FFA reports into dynamic videos via a Wavelet-Flow Variational Autoencoder (WF-VAE) and a diffusion transformer (DiT). Trained on an anonymized dataset, FFA Sora accurately simulates disease features from the input text, as confirmed by objective metrics: Frechet Video Distance (FVD) = 329.78, Learned Perceptual Image Patch Similarity (LPIPS) = 0.48, and Visual-question-answering Score (VQAScore) = 0.61. Specific evaluations showed acceptable alignment between the generated videos and textual prompts, with BERTScore of 0.35. Additionally, the model demonstrated strong privacy-preserving performance in retrieval evaluations, achieving an average Recall@K of 0.073. Human assessments indicated satisfactory visual quality, with an average score of 1.570(scale: 1 = best, 5 = worst). This model addresses privacy concerns associated with sharing large-scale FFA data and enhances medical education.

cs.CV↗

arXiv2024

The Impact of Autonomous Vehicles on Ride-Hailing Platforms with Strategic Human Drivers

Motivated by the rapid development of autonomous vehicle technology, this work focuses on the challenges of introducing them in ride-hailing platforms with conventional strategic human drivers. We consider a ride-hailing platform that operates a mixed fleet of autonomous vehicles (AVs) and conventional vehicles (CVs), where AVs are fully controlled by the platform and CVs are operated by self-interested human drivers. Each vehicle is modelled as a Markov Decision Process that maximizes long-run average reward by choosing its repositioning actions. The behavior of the CVs corresponds to a large game where agents interact through resource constraints that result in queuing delays. In our fluid model, drivers may wait in queues in the different regions when the supply of drivers tends to exceed the service demand by customers. Our primary objective is to optimize the mixed AV-CV system so that the total profit of the platform generated by AVs and CVs is maximized. To achieve that, we formulate this problem as a bi-level optimization problem OPT where the platform moves first by controlling the actions of the AVs and the demand revealed to CVs, and then the CVs react to the revealed demand by forming an equilibrium that can be characterized by the solution of a convex optimization problem. We prove several interesting structural properties of the optimal solution and analyze simple heuristics such as AV-first where we solve for the optimal dispatch of AVs without taking into account the subsequent reaction of the CVs. We propose three numerical algorithms to solve OPT which is a non-convex problem in the platform decision parameters. We evaluate their performance and use them to show some interesting trends in the optimal AV-CV fleet dimensioning when supply is exogenous and endogenous.

cs.GT↗

arXiv2023

Adaptive Control Strategy for Quadruped Robots in Actuator Degradation Scenarios

Quadruped robots have strong adaptability to extreme environments but may also experience faults. Once these faults occur, robots must be repaired before returning to the task, reducing their practical feasibility. One prevalent concern among these faults is actuator degradation, stemming from factors like device aging or unexpected operational events. Traditionally, addressing this problem has relied heavily on intricate fault-tolerant design, which demands deep domain expertise from developers and lacks generalizability. Learning-based approaches offer effective ways to mitigate these limitations, but a research gap exists in effectively deploying such methods on real-world quadruped robots. This paper introduces a pioneering teacher-student framework rooted in reinforcement learning, named Actuator Degradation Adaptation Transformer (ADAPT), aimed at addressing this research gap. This framework produces a unified control strategy, enabling the robot to sustain its locomotion and perform tasks despite sudden joint actuator faults, relying exclusively on its internal sensors. Empirical evaluations on the Unitree A1 platform validate the deployability and effectiveness of Adapt on real-world quadruped robots, and affirm the robustness and practicality of our approach.

cs.RO↗

arXiv2023

Two new classes of exponential Runge-Kutta integrators for efficiently solving stiff systems or highly oscillatory problems

We note a fact that stiff systems or differential equations that have highly oscillatory solutions cannot be solved efficiently using conventional methods. In this paper, we study two new classes of exponential Runge-Kutta (ERK) integrators for efficiently solving stiff systems or highly oscillatory problems. We first present a novel class of explicit modified version of exponential Runge-Kutta (MVERK) methods based on the order conditions. Furthermore, we consider a class of explicit simplified version of exponential Runge-Kutta (SVERK) methods. Numerical results demonstrate the high efficiency of the explicit MVERK integrators and SVERK methods derived in this paper compared with the well-known explicit ERK integrators for stiff systems or highly oscillatory problems in the literature.

math.NA↗

arXiv2023

Aerial IRS with Robotic Anchoring Capabilities: A Novel Way for Adaptive Coverage Enhancement

It is widely accepted that integrating intelligent reflecting surfaces (IRSs) with unmanned aerial vehicles (UAV) or drones can assist wireless networks in improving network coverage and end user Quality of Service (QoS). However, the critical constrain of drones is their very limited hovering/flying time. In this paper we propose the concept of robotic aerial IRSs (RA-IRSs), which are in essence drones that in addition to IRS embed an anchoring mechanism that allows them to grasp in an energy neutral manner at tall urban landforms such as lampposts. By doing so, RA-IRSs can completely eliminate the flying/hovering energy consumption and can offer service for multiple hours or even days (something not possible with UAV-mounted IRSs). Using that property we show how RA-IRS can increase network performance by changing their anchoring location to follow the spatio-temporal traffic demand. The proposed methodology, developed through Integer Linear Programming (ILP) formulations offers a significant Signal-to-Noise (SNR) gain in highly heterogeneous regions in terms of traffic demand compared to fixed IRS; hence, addressing urban coverage discrepancies effectively. Numerical simulations validate the superiority of RA-IRSs over fixed terrestrial IRSs in terms of traffic serviceability, sustaining more than 2 times the traffic demand in areas experiencing high heterogeneity, emphasizing their adaptability in improving coverage and QoS in complex urban terrains.

cs.NI↗

arXiv2023

How should the server sleep? -- Age-energy tradeoff in sleep-wake server systems

The surging demand for fresh information from various Internet of Things (IoT) applications requires oceans of data sampled from the physical environment to be transmitted and processed timely, which would lead to huge energy consumption. We investigate the sleep-wake strategies of servers in communication systems to reduce energy consumption while guaranteeing timely delivery of fresh information to users. Specifically, we investigate a multi-source single-server queueing system and propose a novel sleep-wake strategy called the Conditional Sleep (CS) scheme. Our analysis reveals that the CS scheme outperforms the widely-used Hysteresis Time (HT) and Bernoulli Sleep (BS) schemes in terms of Age of Information (AoI), while retaining the same energy consumption rate and Peak Age of Information (PAoI). We find that increasing the sleep period length leads to a reduction in energy consumption and an increase in PAoI, but it does not always increase AoI. Moreover, we show that using PAoI as the information freshness metric in designing sleep-wake strategies would make the server sleep infinitely long due to the PAoI being determined by first-order statistics. We further numerically show that having the bufferless system can achieve a better PAoI-energy tradeoff than the infinite buffer system when having a large sampling rate.

cs.IT↗

arXiv2021

A two-step symmetric method for charged-particle dynamics in a normal or strong magnetic feld

The study of the long time conservation for numerical methods poses interesting and challenging questions from the point of view of geometric integration. In this paper, we analyze the long time energy and magnetic moment conservations of two-step symmetric methods for charged-particle dynamics. A two-step symmetric method is proposed and its long time behaviour is shown not only in a normal magnetic feld but also in a strong magnetic feld. The approaches to dealing with these two cases are based on the backward error analysis and modulated Fourier expansion, respectively. It is obtained from the analysis that the method has better long time conservations than the variational method which was researched recently in the literature.

math.NA↗

arXiv2021

General local energy-preserving integrators for solving multi-symplectic Hamiltonian PDEs

In this paper we propose and investigate a general approach to constructing local energy-preserving algorithms which can be of arbitrarily high order in time for solving Hamiltonian PDEs. This approach is based on the temporal discretization using continuous Runge-Kutta-type methods, and the spatial discretization using pseudospectral methods or Gauss--Legendre collocation methods. The local energy conservation law of our new schemes is analyzed in detail. The effectiveness of the novel local energy-preserving integrators is demonstrated by coupled nonlinear Schrödinger equations and 2D nonlinear Schrödinger equations with external fields. Our new schemes are compared with some classical multi-symplectic and symplectic schemes in numerical experiments. The numerical results show the remarkable \emph{long-term} behaviour of our new schemes.

math.NA↗

arXiv2020

Exponential integrators preserving first integrals or Lyapunov functions for conservative or dissipative systems

In this paper, combining the ideas of exponential integrators and discrete gradients, we propose and analyze a new structure-preserving exponential scheme for the conservative or dissipative system $\dot{y} = Q(M y + \nabla U (y))$, where $Q$ is a $d\times d$ skew-symmetric or negative semidefinite real matrix, $M$ is a $d\times d$ symmetric real matrix, and $U : \mathbb{R}^d\rightarrow\mathbb{R}$ is a differentiable function. We present two properties of the new scheme. The paper is accompanied by numerical results that demonstrate the remarkable superiority of our new scheme in comparison with other structure-preserving schemes in the scientific literature.

math.NA↗

arXiv2020

Functionally-fitted energy-preserving methods for solving oscillatory nonlinear Hamiltonian systems

In the last few decades, numerical simulation for nonlinear oscillators has received a great deal of attention, and many researchers have been concerned with the design and analysis of numerical methods for solving oscillatory problems. In this paper, from the perspective of the continuous finite element method, we propose and analyze new energy-preserving functionally fitted methods, in particular trigonometrically fitted methods of an arbitrarily high order for solving oscillatory nonlinear Hamiltonian systems with a fixed frequency. To implement these new methods in a widespread way, they are transformed into a class of continuous-stage Runge--Kutta methods. This paper is accompanied by numerical experiments on oscillatory Hamiltonian systems such as the FPU problem and nonlinear Schrödinger equation. The numerical results demonstrate the remarkable accuracy and efficiency of our new methods compared with the existing high-order energy-preserving methods in the literature.

math.NA↗

arXiv2018

Long-time momentum and actions behaviour of energy-preserving methods for semilinear wave equations via spatial spectral semi-discretizations

As is known that wave equations have physically very important properties which should be respected by numerical schemes in order to predict correctly the solution over a long time period. In this paper, the long-time behaviour of momentum and actions for energy-preserving methods is analysed for semilinear wave equations. A full discretisation of wave equations is derived and analysed by firstly using a spectral semi-discretisation in space and then by applying the adopted average vector field (AAVF) method in time. This numerical scheme can exactly preserve the energy of the semi-discrete system. The main theme of this paper is to analyse another important physical property of the scheme. It is shown that this scheme yields near conservation of a modified momentum and modified actions over long times. Both the results are rigorously proved based on the technique of modulated Fourier expansions in two stages. First a multi-frequency modulated Fourier expansion of the AAVF method is constructed and then two almost-invariants of the modulation system are derived.

math.NA↗

arXiv2018

Long-time oscillatory energy conservation of total energy-preserving methods for highly oscillatory Hamiltonian systems

For an integrator when applied to a highly oscillatory system, the near conservation of the oscillatory energy over long times is an important aspect. In this paper, we study the long-time near conservation of oscillatory energy for the adopted average vector field (AAVF) method when applied to highly oscillatory Hamiltonian systems. This AAVF method is an extension of the average vector field method and preserves the total energy of highly oscillatory Hamiltonian systems exactly. This paper is devoted to analysinganother important property of AAVF method, i.e., the near conservation of its oscillatory energy in a long term. The long-time oscillatory energy conservation is obtained via constructing a modulated Fourier expansion of the AAVF method and deriving an almost invariant of the expansion. A similar result of the method in the multi-frequency case is also presented in this paper.

math.NA↗

arXiv2018

Volume-preserving exponential integrators

As is known that various dynamical systems including all Hamiltonian systems preserve volume in phase space. This qualitative geometrical property of the analytical solution should be respected in the sense of Geometric Integration. This paper analyses the volume-preserving property of exponential integrators in different vector fields. We derive a necessary and sufficient condition of volume preservation for exponential integrators, and with this condition, volume-preserving exponential integrators are analysed in detail for four kinds of vector fields. It turns out that symplectic exponential integrators can be volume preserving for a much larger class of vector fields than Hamiltonian systems. On the basis of the analysis, novel volume-preserving exponential integrators are derived for solving highly oscillatory second-order systems and extended Runge--Kutta--Nystr\"{o}m (ERKN) integrators of volume preservation are presented for separable partitioned systems. Moreover, the volume preservation of Runge--Kutta--Nystr\"{o}m (RKN) methods is also discussed. Four illustrative numerical experiments are carried out to demonstrate the notable superiority of volume-preserving exponential integrators in comparison with volume-preserving Runge-Kutta methods.

math.NA↗