arXiv subjects

Mengyu Wang

Publications and source records attributed to Mengyu Wang.

At least 73 records · Page 4Linked to original sources

arXiv2025

FairFedMed: Benchmarking Group Fairness in Federated Medical Imaging with FairLoRA

Fairness remains a critical concern in healthcare, where unequal access to services and treatment outcomes can adversely affect patient health. While Federated Learning (FL) presents a collaborative and privacy-preserving approach to model training, ensuring fairness is challenging due to heterogeneous data across institutions, and current research primarily addresses non-medical applications. To fill this gap, we establish the first experimental benchmark for fairness in medical FL, evaluating six representative FL methods across diverse demographic attributes and imaging modalities. We introduce FairFedMed, the first medical FL dataset specifically designed to study group fairness (i.e., demographics). It comprises two parts: FairFedMed-Oph, featuring 2D fundus and 3D OCT ophthalmology samples with six demographic attributes; and FairFedMed-Chest, which simulates real cross-institutional FL using subsets of CheXpert and MIMIC-CXR. Together, they support both simulated and real-world FL across diverse medical modalities and demographic groups. Existing FL models often underperform on medical images and overlook fairness across demographic groups. To address this, we propose FairLoRA, a fairness-aware FL framework based on SVD-based low-rank approximation. It customizes singular value matrices per demographic group while sharing singular vectors, ensuring both fairness and efficiency. Experimental results on the FairFedMed dataset demonstrate that FairLoRA not only achieves state-of-the-art performance in medical image classification but also significantly improves fairness across diverse populations. Our code and dataset can be accessible via link: https://wang.hms.harvard.edu/fairfedmed/.

cs.CY↗

arXiv2025

CharaConsist: Fine-Grained Consistent Character Generation

In text-to-image generation, producing a series of consistent contents that preserve the same identity is highly valuable for real-world applications. Although a few works have explored training-free methods to enhance the consistency of generated subjects, we observe that they suffer from the following problems. First, they fail to maintain consistent background details, which limits their applicability. Furthermore, when the foreground character undergoes large motion variations, inconsistencies in identity and clothing details become evident. To address these problems, we propose CharaConsist, which employs point-tracking attention and adaptive token merge along with decoupled control of the foreground and background. CharaConsist enables fine-grained consistency for both foreground and background, supporting the generation of one character in continuous shots within a fixed scene or in discrete shots across different scenes. Moreover, CharaConsist is the first consistent generation method tailored for text-to-image DiT model. Its ability to maintain fine-grained consistency, combined with the larger capacity of latest base model, enables it to produce high-quality visual outputs, broadening its applicability to a wider range of real-world scenarios. The source code has been released at https://github.com/Murray-Wang/CharaConsist

cs.CV↗

arXiv2025

Pre-training Time Series Models with Stock Data Customization

Stock selection, which aims to predict stock prices and identify the most profitable ones, is a crucial task in finance. While existing methods primarily focus on developing model structures and building graphs for improved selection, pre-training strategies remain underexplored in this domain. Current stock series pre-training follows methods from other areas without adapting to the unique characteristics of financial data, particularly overlooking stock-specific contextual information and the non-stationary nature of stock prices. Consequently, the latent statistical features inherent in stock data are underutilized. In this paper, we propose three novel pre-training tasks tailored to stock data characteristics: stock code classification, stock sector classification, and moving average prediction. We develop the Stock Specialized Pre-trained Transformer (SSPT) based on a two-layer transformer architecture. Extensive experimental results validate the effectiveness of our pre-training methods and provide detailed guidance on their application. Evaluations on five stock datasets, including four markets and two time periods, demonstrate that SSPT consistently outperforms the market and existing methods in terms of both cumulative investment return ratio and Sharpe ratio. Additionally, our experiments on simulated data investigate the underlying mechanisms of our methods, providing insights into understanding price series. Our code is publicly available at: https://github.com/astudentuser/Pre-training-Time-Series-Models-with-Stock-Data-Customization.

cs.CE↗

arXiv2025

SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing

Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright infringement. Concept erasing finetunes weights to unlearn undesirable concepts, and has emerged as a promising solution. However, existing methods treat unsafe concept as a fixed word and repeatedly erase it, trapping DMs in ``word concept abyss'', which prevents generalized concept-related erasing. To escape this abyss, we introduce semantic-augment erasing which transforms concept word erasure into concept domain erasure by the cyclic self-check and self-erasure. It efficiently explores and unlearns the boundary representation of concept domain through semantic spatial relationships between original and training DMs, without requiring additional preprocessed data. Meanwhile, to mitigate the retention degradation of irrelevant concepts while erasing unsafe concepts, we further propose the global-local collaborative retention mechanism that combines global semantic relationship alignment with local predicted noise preservation, effectively expanding the retentive receptive field for irrelevant concepts. We name our method SAGE, and extensive experiments demonstrate the comprehensive superiority of SAGE compared with other methods in the safe generation of DMs. The code and weights will be open-sourced at https://github.com/KevinLight831/SAGE.

cs.CV↗

arXiv2025

How Secure Are Large Language Models (LLMs) for Navigation in Urban Environments?

In the field of robotics and automation, navigation systems based on Large Language Models (LLMs) have recently demonstrated impressive performance. However, the security aspects of these systems have received relatively less attention. This paper pioneers the exploration of vulnerabilities in LLM-based navigation models in urban outdoor environments, a critical area given the widespread application of this technology in autonomous driving, logistics, and emergency services. Specifically, we introduce a novel Navigational Prompt Attack that manipulates LLM-based navigation models by perturbing the original navigational prompt, leading to incorrect actions. Based on the method of perturbation, our attacks are divided into two types: Navigational Prompt Insert (NPI) Attack and Navigational Prompt Swap (NPS) Attack. We conducted comprehensive experiments on an LLM-based navigation model that employs various LLMs for reasoning. Our results, derived from the Touchdown and Map2Seq street-view datasets under both few-shot learning and fine-tuning configurations, demonstrate notable performance declines across seven metrics in the face of both white-box and black-box attacks. Moreover, our attacks can be easily extended to other LLM-based navigation models with similarly effective results. These findings highlight the generalizability and transferability of the proposed attack, emphasizing the need for enhanced security in LLM-based navigation systems. As an initial countermeasure, we propose the Navigational Prompt Engineering (NPE) Defense strategy, which concentrates on navigation-relevant keywords to reduce the impact of adversarial attacks. While initial findings indicate that this strategy enhances navigational safety, there remains a critical need for the wider research community to develop stronger defense methods to effectively tackle the real-world challenges faced by these systems.

cs.RO↗

arXiv2025

Evaluation of In Vivo Subject-Specific Mechanical Modeling of the Optic Nerve Head for Robust Assessment of Ocular Mechanics

To establish the tissue regions necessary to accurately represent the mechanics of the optic nerve head (ONH), imaging data of the ONH from 2 healthy subjects were used to create in vivo subject-specific eye mechanical models considering distinct properties for all major ocular tissues. Tests were performed to evaluate the effect of the material properties and the inclusion of these tissues on the mechanics of the lamina cribrosa (LC), retina, and optic nerve. Then, the LC mechanical response due to variations in intraocular and intracranial pressures was evaluated to validate the modeling approach. The sclera stiffness has the largest impact on the mechanics of the LC, retina, and optic nerve, while Bruchs membrane has a negligible effect on these tissues response. The validation tests showed increased LC strain with increased pressure and highest strains in the inferior and temporal subregion, as seen in literature studies. Consequently, accurate ONH mechanical representation can be obtained by only including those tissue regions identified as necessary.

physics.med-ph↗

arXiv2025

A Complex-valued SAR Foundation Model Based on Physically Inspired Representation Learning

Vision foundation models in remote sensing have been extensively studied due to their superior generalization on various downstream tasks. Synthetic Aperture Radar (SAR) offers all-day, all-weather imaging capabilities, providing significant advantages for Earth observation. However, establishing a foundation model for SAR image interpretation inevitably encounters the challenges of insufficient information utilization and poor interpretability. In this paper, we propose a remote sensing foundation model based on complex-valued SAR data, which simulates the polarimetric decomposition process for pre-training, i.e., characterizing pixel scattering intensity as a weighted combination of scattering bases and scattering coefficients, thereby endowing the foundation model with physical interpretability. Specifically, we construct a series of scattering queries, each representing an independent and meaningful scattering basis, which interact with SAR features in the scattering query decoder and output the corresponding scattering coefficient. To guide the pre-training process, polarimetric decomposition loss and power self-supervision loss are constructed. The former aligns the predicted coefficients with Yamaguchi coefficients, while the latter reconstructs power from the predicted coefficients and compares it to the input image's power. The performance of our foundation model is validated on six typical downstream tasks, achieving state-of-the-art results. Notably, the foundation model can extract stable feature representations and exhibits strong generalization, even in data-scarce conditions.

cs.CV↗

arXiv2025

FairDiffusion: Enhancing Equity in Latent Diffusion Models via Fair Bayesian Perturbation

Recent progress in generative AI, especially diffusion models, has demonstrated significant utility in text-to-image synthesis. Particularly in healthcare, these models offer immense potential in generating synthetic datasets and training medical students. However, despite these strong performances, it remains uncertain if the image generation quality is consistent across different demographic subgroups. To address this critical concern, we present the first comprehensive study on the fairness of medical text-to-image diffusion models. Our extensive evaluations of the popular Stable Diffusion model reveal significant disparities across gender, race, and ethnicity. To mitigate these biases, we introduce FairDiffusion, an equity-aware latent diffusion model that enhances fairness in both image generation quality as well as the semantic correlation of clinical features. In addition, we also design and curate FairGenMed, the first dataset for studying the fairness of medical generative models. Complementing this effort, we further evaluate FairDiffusion on two widely-used external medical datasets: HAM10000 (dermatoscopic images) and CheXpert (chest X-rays) to demonstrate FairDiffusion's effectiveness in addressing fairness concerns across diverse medical imaging modalities. Together, FairDiffusion and FairGenMed significantly advance research in fair generative learning, promoting equitable benefits of generative AI in healthcare.

cs.CV↗

arXiv2025

Socially-Aware Robot Navigation Enhanced by Bidirectional Natural Language Conversations Using Large Language Models

Robot navigation is crucial across various domains, yet traditional methods focus on efficiency and obstacle avoidance, often overlooking human behavior in shared spaces. With the rise of service robots, socially aware navigation has gained prominence. However, existing approaches primarily predict pedestrian movements or issue alerts, lacking true human-robot interaction. We introduce Hybrid Soft Actor-Critic with Large Language Model (HSAC-LLM), a novel framework for socially aware navigation. By integrating deep reinforcement learning with large language models, HSAC-LLM enables bidirectional natural language interactions, predicting both continuous and discrete navigation actions. When potential collisions arise, the robot proactively communicates with pedestrians to determine avoidance strategies. Experiments in 2D simulation, Gazebo, and real-world environments demonstrate that HSAC-LLM outperforms state-of-the-art DRL methods in interaction, navigation, and obstacle avoidance. This paradigm advances effective human-robot interactions in dynamic settings. Videos are available at https://hsacllm.github.io/.

cs.RO↗

arXiv2025

Evolution and sudden change of steady interactions of low enthalpy hypersonic double wedge flows with fore angle

The evolution and sudden change of steady interaction structures is numerically studied with the fore wedge angle theta_1 in a low enthalpy hypersonic double wedge configuration. It particularly focuses on the conditions of Swantek and Austin's experiments where Ma=7, and h_0=2 MJ/kg but with a reduced Reynolds number (Re). The sudden structural change indicates that when theta_1 reaches a critical value, minor angular variations can trigger a discontinuous transformation in flow structures. The analysis is based on the laminar Navier-Stokes equations, using ideal gas and non-equilibrium gas models. Under the condition of Re=1E5/m, detailed numerical simulations are conducted as theta_1 varies over 0 deg-40 deg. This study yields the following findings: (a) The upper and lower boundaries of theta_1 for the onset of unsteady flow are identified. When theta_1 lies outside these boundaries, the flow remains steady. (b) As theta_1 increases, the interaction patterns evolve sequentially, progressing from Type VI through Type VI->V, Type III, Type IV_r, and ultimately to a flow dominated solely by a bow shock. This evolution defines the boundaries between different interaction patterns and provides a comprehensive understanding of their progression with theta_1. Sudden structural changes occur during the transitions from Type III to Type IV_r and from Type IV_r to a bow shock-dominated flow. In addition, a comparative study is performed through shock polar analysis to compare its predictions with computational results. (c) An unconventional reflection pattern of the transmitted shock over the separation zone, called Type III_r, is observed in non-equilibrium gas flows, which differs from classical interaction patterns. (d) The aerodynamic distribution of wall properties under various interactions is obtained, indicating distinct features before and after the sudden structural change.

physics.flu-dyn↗

arXiv2024

Design of a variable-Mach-number waverider by the osculating-curved-cone method using a rational distribution function and incorporating the equilibrium-gas model

When a waverider flies at hypersonic speed, the thermodynamic properties of the surrounding gas change because of the rapid increase in temperature, so it is reasonable to consider real-gas effects in the vehicle design. In addition, a hypersonic waverider usually travels at varying speed during flight, and deviating from the default speed designed in terms of a constant Mach number often creates difficulties in preserving the expected performance. Therefore, research on the design of variable-Mach-number waveriders considering equilibrium-gas effects is important for applications. In this paper, a design method for a variable-Mach-number osculating-curved-cone waverider (VMOCCW) considering equilibrium-gas effects is introduced, then the influences of different gas models on the waverider design are studied by taking a VMOCCW designed with a linear Mach-number distribution as an example. Furthermore, a new Mach-number distribution method is proposed by using a parameterized rational function, which is combined with different gas models to achieve VMOCCW design. For comparison, waveriders designed with quadratic concave and convex increasing functions are also selected for comparison of their layouts and aerodynamic performances under design and off-design conditions. The results show that waveriders designed with the equilibrium-gas model exhibit differences in geometric features (e.g., volume and volumetric efficiency) and aerodynamic characteristics (e.g., lift-to-drag ratio and pitching moment coefficient) compared to those designed with the ideal-gas model. Specifically, waveriders designed with a rational function for the Ma distribution have a wing-like structure, and overall they have more-balanced geometric and aerodynamic characteristics than those designed with quadratic concave and convex functions.

physics.flu-dyn↗

arXiv2024

TransFair: Transferring Fairness from Ocular Disease Classification to Progression Prediction

The use of artificial intelligence (AI) in automated disease classification significantly reduces healthcare costs and improves the accessibility of services. However, this transformation has given rise to concerns about the fairness of AI, which disproportionately affects certain groups, particularly patients from underprivileged populations. Recently, a number of methods and large-scale datasets have been proposed to address group performance disparities. Although these methods have shown effectiveness in disease classification tasks, they may fall short in ensuring fair prediction of disease progression, mainly because of limited longitudinal data with diverse demographics available for training a robust and equitable prediction model. In this paper, we introduce TransFair to enhance demographic fairness in progression prediction for ocular diseases. TransFair aims to transfer a fairness-enhanced disease classification model to the task of progression prediction with fairness preserved. Specifically, we train a fair EfficientNet, termed FairEN, equipped with a fairness-aware attention mechanism using extensive data for ocular disease classification. Subsequently, this fair classification model is adapted to a fair progression prediction model through knowledge distillation, which aims to minimize the latent feature distances between the classification and progression prediction models. We evaluate FairEN and TransFair for fairness-enhanced ocular disease classification and progression prediction using both two-dimensional (2D) and 3D retinal images. Extensive experiments and comparisons with models with and without considering fairness learning show that TransFair effectively enhances demographic equity in predicting ocular disease progression.

cs.LG↗

arXiv2024

Modeling News Interactions and Influence for Financial Market Prediction

The diffusion of financial news into market prices is a complex process, making it challenging to evaluate the connections between news events and market movements. This paper introduces FININ (Financial Interconnected News Influence Network), a novel market prediction model that captures not only the links between news and prices but also the interactions among news items themselves. FININ effectively integrates multi-modal information from both market data and news articles. We conduct extensive experiments on two datasets, encompassing the S&P 500 and NASDAQ 100 indices over a 15-year period and over 2.7 million news articles. The results demonstrate FININ's effectiveness, outperforming advanced market prediction models with an improvement of 0.429 and 0.341 in the daily Sharpe ratio for the two markets respectively. Moreover, our results reveal insights into the financial news, including the delayed market pricing of news, the long memory effect of news, and the limitations of financial sentiment analysis in fully extracting predictive power from news data.

cs.CE↗

arXiv2024

Numerical studies on steady interaction of low enthalpy hypersonic double wedge flows using different gas models

Numerical investigations and analyses are carried out particularly on the steady interactions of low enthalpy hypersonic 30-55-deg double wedge configuration at conditions similar to the experimental setup by Swantek & Austin. To achieve a steady solution, Re lower than those in the experiment are used. Three gas models, i.e., the perfect, equilibrium, and non-equilibrium gas models, are used to analyze the difference potentials that arise from the physical model. Grid convergence studies are first conducted at Ma=7 and Re=2.5e5/m. Subsequently, comprehensive numerical studies are carried out on the steady interactions and their evolution at Ma=7 and h0=2.1MJ/kg. Specifically: (a) The upper limits of Re are identified where the flows remain steady, and the corresponding interaction characteristics as well as differences in the three gas models are investigated. Notably, a quasi-normal shock wave is observed within the slip line passage in the case of the perfect gas model. (b) The flow characteristics of the three models, including the interaction pattern, geometric features of triple points, impingements, and separation zone, are studied and compared for Re=(4,3,2)e4/m. Differences primarily emerge between the results of the perfect gas model and the real gas model. Specifically, a transmitted shock reflecting above the separation zone is observed in the case of the perfect gas model. The effect of the gas model on temperature and specific heat ratio distributions, as well as the heat transfer and pressure coefficients over the wedge surface are investigated. The shock polar method is applied for comparison with computational results, while a 1D flow model is proposed to explain the occurrence of the quasi-normal shock wave. Finally, the effects of variations in Mach number and enthalpy are determined, by alternatively varying the two parameters around Ma=7 and h0=2.1MJ/kg at Re=4e4/m.

physics.flu-dyn↗

arXiv2024

MANA-Net: Mitigating Aggregated Sentiment Homogenization with News Weighting for Enhanced Market Prediction

It is widely acknowledged that extracting market sentiments from news data benefits market predictions. However, existing methods of using financial sentiments remain simplistic, relying on equal-weight and static aggregation to manage sentiments from multiple news items. This leads to a critical issue termed ``Aggregated Sentiment Homogenization'', which has been explored through our analysis of a large financial news dataset from industry practice. This phenomenon occurs when aggregating numerous sentiments, causing representations to converge towards the mean values of sentiment distributions and thereby smoothing out unique and important information. Consequently, the aggregated sentiment representations lose much predictive value of news data. To address this problem, we introduce the Market Attention-weighted News Aggregation Network (MANA-Net), a novel method that leverages a dynamic market-news attention mechanism to aggregate news sentiments for market prediction. MANA-Net learns the relevance of news sentiments to price changes and assigns varying weights to individual news items. By integrating the news aggregation step into the networks for market prediction, MANA-Net allows for trainable sentiment representations that are optimized directly for prediction. We evaluate MANA-Net using the S&P 500 and NASDAQ 100 indices, along with financial news spanning from 2003 to 2018. Experimental results demonstrate that MANA-Net outperforms various recent market prediction methods, enhancing Profit & Loss by 1.1% and the daily Sharpe ratio by 0.252.

cs.LG↗

arXiv2024

Randomized dual singular value decomposition

We first propose a concise singular value decomposition of dual matrices. Then, the randomized version of the decomposition is presented. It can significantly reduce the computational cost while maintaining the similar accuracy. We analyze the theoretical properties and illuminate the numerical performance of the randomized algorithm.

math.NA↗

arXiv2024

FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification

Addressing fairness in artificial intelligence (AI), particularly in medical AI, is crucial for ensuring equitable healthcare outcomes. Recent efforts to enhance fairness have introduced new methodologies and datasets in medical AI. However, the fairness issue under the setting of domain transfer is almost unexplored, while it is common that clinics rely on different imaging technologies (e.g., different retinal imaging modalities) for patient diagnosis. This paper presents FairDomain, a pioneering systemic study into algorithmic fairness under domain shifts, employing state-of-the-art domain adaptation (DA) and generalization (DG) algorithms for both medical segmentation and classification tasks to understand how biases are transferred between different domains. We also introduce a novel plug-and-play fair identity attention (FIA) module that adapts to various DA and DG algorithms to improve fairness by using self-attention to adjust feature importance based on demographic attributes. Additionally, we curate the first fairness-focused dataset with two paired imaging modalities for the same patient cohort on medical segmentation and classification tasks, to rigorously assess fairness in domain-shift scenarios. Excluding the confounding impact of demographic distribution variation between source and target domains will allow clearer quantification of the performance of domain transfer models. Our extensive evaluations reveal that the proposed FIA significantly enhances both model performance accounted for fairness across all domain shift settings (i.e., DA and DG) with respect to different demographics, which outperforms existing methods on both segmentation and classification. The code and data can be accessed at https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k.

eess.IV↗

arXiv2024

FairDiff: Fair Segmentation with Point-Image Diffusion

Fairness is an important topic for medical image analysis, driven by the challenge of unbalanced training data among diverse target groups and the societal demand for equitable medical quality. In response to this issue, our research adopts a data-driven strategy-enhancing data balance by integrating synthetic images. However, in terms of generating synthetic images, previous works either lack paired labels or fail to precisely control the boundaries of synthetic images to be aligned with those labels. To address this, we formulate the problem in a joint optimization manner, in which three networks are optimized towards the goal of empirical risk minimization and fairness maximization. On the implementation side, our solution features an innovative Point-Image Diffusion architecture, which leverages 3D point clouds for improved control over mask boundaries through a point-mask-image synthesis pipeline. This method outperforms significantly existing techniques in synthesizing scanning laser ophthalmoscopy (SLO) fundus images. By combining synthetic data with real data during the training phase using a proposed Equal Scale approach, our model achieves superior fairness segmentation performance compared to the state-of-the-art fairness learning models. Code is available at https://github.com/wenyi-li/FairDiff.

cs.CV↗