arXiv subjects

Ying Cao

Publications and source records attributed to Ying Cao.

At least 37 records · Page 2Linked to original sources

arXiv2025

Decentralized Adversarial Training over Graphs

The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years. Most existing studies focus on the behavior of stand-alone single-agent learners. In comparison, this work studies adversarial training over graphs, where individual agents are subjected to perturbations of varied strength levels across space. It is expected that interactions by linked agents, and the heterogeneity of the attack models that are possible over the graph, can help enhance robustness in view of the coordination power of the group. Using a min-max formulation of distributed learning, we develop a decentralized adversarial training framework for multi-agent systems. Specifically, we devise two decentralized adversarial training algorithms by relying on two popular decentralized learning strategies--diffusion and consensus. We analyze the convergence properties of the proposed framework for strongly-convex, convex, and non-convex environments, and illustrate the enhanced robustness to adversarial attacks.

cs.LG↗

arXiv2025

Characterizing Discourse Group Roles in Inquiry-based University Science Labs

Group work is commonly adopted in university science laboratories. However, student small-group discourse in university science labs is rarely investigated. We aim to bridge the gap in the literature by characterizing student discourse group roles in inquiry-based science labs. The instructional context for the study was a summer program hosted at a private research university in the eastern United States. The program was designed as a bridge program for matriculating students who were first generation and/or deaf or hard-of-hearing (DHH). Accommodations such as interpreters and technology were provided for DHH students. We analyzed 19 students' discourse moves in five lab activities from the video recordings, resulting in a total of 48 student-lab units. We developed codes to describe student discourse moves: asking a question, proposing an idea, participating in discussion, chatting off-task, and talking with instructor. Through a cluster analysis using the 48 student-lab units on quantified discourse moves, we identified four discourse styles, High on-task high social, High on-task low social, Low on-task low social, and Low on-task high social. The results show that individual students tend to demonstrate varying discourse styles in different lab activities; students' discourse styles within the same groups tend to be aligned with their group members. By examining group members' discourse styles in mixed-gender groups, we did not observe a difference in engagement level between female and male students. DHH students in mixed hearing ability groups, however, were observed to have a lower level of engagement compared to their non-DHH group members. We discuss possible factors that may have contributed to the observations for genders and students with different hearing abilities. We also provide suggestions for promoting equitable small-group discourse in university science labs.

physics.ed-ph↗

arXiv2025

Edge states in super honeycomb structures with PT-symmetric deformations

The existence of edge states is one of the most vital properties of topological insulators. Although tremendous success has been accomplished in describing and explaining edge states associated with PT symmetry breaking, little work has been done on PT symmetry preserving cases. Two-dimensional Schroedinger operators with super honeycomb lattice potentials always have double Dirac cones at the Gamma point - the zero momentum point on their energy bands due to C6 symmetry, PT symmetry, and the "folding" symmetry - caused by an additional translation symmetry. There are two topologically different ways to deform such a system by PT symmetry preserving but folding symmetry breaking perturbations. Interestingly, there exist two gapped edge states on the interface between such two kinds of perturbed materials. In this paper, we illustrate the existence of such PT preserving edge states rigorously for the first time. We use a domain wall modulated Schroedinger operator to model the phenomenon under small perturbations and rigorously prove the existence of two gapped edge states. We also provide a brief interpretation from the point of view of "topology" by the parities of degenerate bulk modes. Our work thoroughly explains the existence of "helical" like edge states in super honeycomb configurations and lays a foundation for the descriptions of topologies of such systems.

math-ph↗

arXiv2024

HieraFashDiff: Hierarchical Fashion Design with Multi-stage Diffusion Models

Fashion design is a challenging and complex process.Recent works on fashion generation and editing are all agnostic of the actual fashion design process, which limits their usage in practice.In this paper, we propose a novel hierarchical diffusion-based framework tailored for fashion design, coined as HieraFashDiff. Our model is designed to mimic the practical fashion design workflow, by unraveling the denosing process into two successive stages: 1) an ideation stage that generates design proposals given high-level concepts and 2) an iteration stage that continuously refines the proposals using low-level attributes. Our model supports fashion design generation and fine-grained local editing in a single framework. To train our model, we contribute a new dataset of full-body fashion images annotated with hierarchical text descriptions. Extensive evaluations show that, as compared to prior approaches, our method can generate fashion designs and edited results with higher fidelity and better prompt adherence, showing its promising potential to augment the practical fashion design workflow. Code and Dataset are available at https://github.com/haoli-zbdbc/hierafashdiff.

cs.CV↗

arXiv2024

A No-Reference Medical Image Quality Assessment Method Based on Automated Distortion Recognition Technology: Application to Preprocessing in MRI-guided Radiotherapy

Objective:To develop a no-reference image quality assessment method using automated distortion recognition to boost MRI-guided radiotherapy precision.Methods:We analyzed 106,000 MR images from 10 patients with liver metastasis,captured with the Elekta Unity MR-LINAC.Our No-Reference Quality Assessment Model includes:1)image preprocessing to enhance visibility of key diagnostic features;2)feature extraction and directional analysis using MSCN coefficients across four directions to capture textural attributes and gradients,vital for identifying image features and potential distortions;3)integrative Quality Index(QI)calculation,which integrates features via AGGD parameter estimation and K-means clustering.The QI,based on a weighted MAD computation of directional scores,provides a comprehensive image quality measure,robust against outliers.LOO-CV assessed model generalizability and performance.Tumor tracking algorithm performance was compared with and without preprocessing to verify tracking accuracy enhancements.Results:Preprocessing significantly improved image quality,with the QI showing substantial positive changes and surpassing other metrics.After normalization,the QI's average value was 79.6 times higher than CNR,indicating improved image definition and contrast.It also showed higher sensitivity in detail recognition with average values 6.5 times and 1.7 times higher than Tenengrad gradient and entropy.The tumor tracking algorithm confirmed significant tracking accuracy improvements with preprocessed images,validating preprocessing effectiveness.Conclusions:This study introduces a novel no-reference image quality evaluation method based on automated distortion recognition,offering a new quality control tool for MRIgRT tumor tracking.It enhances clinical application accuracy and facilitates medical image quality assessment standardization, with significant clinical and research value.

eess.IV↗

arXiv2024

Competitive Analysis of Online Path Selection: Impacts of Path Length, Topology, and System-Level Costs

Consider a communication network to which a sequence of self-interested users come and send requests for data transmission between nodes. This work studies the question of how to guide the path selection choices made by those online-arriving users and maximize the social welfare. Competitive analysis is the main technical tool. Specifically, the impacts of path length bounds and topology on the competitive ratio of the designed algorithm are analyzed theoretically and explored experimentally. We observe intricate and interesting relationships between the empirical performance and the studied network parameters, which shed some light on how to design the network. We also investigate the influence of system-level costs on the optimal algorithm design.

cs.DS↗

arXiv2024

Analyzing students collaboratively solving spherical unit vector problems in upper level E and M through a lens of shared resources

We are interested in better understanding ways that students collaborate to solve conceptual physics problems in the context of spherical unit vectors in upper-level E&M, especially problems that have been shown to be difficult for students to solve individually on their own, but which groups of students have been more successful at. Using think-aloud interviews with students in small groups, we ask them to solve together on a large whiteboard conceptual problems from this E&M context. The interviews were video and audio recorded, and qualitatively analyzed using an emergent coding method and the resources framework. Through this analysis, we observed one common mechanism in all three group-interviews whereby students collaborated effectively: first one student activated a conceptual resource and expressed it, then another student took up that idea, and finally the whole group together used that idea to move forward with the problem. This mechanism exemplifies a newer framework: shared resources. We further analyzed students' collaboration through the lens of shared resources and identified multiple instances. We propose that the shared resources construct could be a potential tool to help understand how students collaborate in solving conceptual physics problems. In this paper, we report our methodology and the results from one group interview to illustrate one shared resource we identified and the role it played in helping students collaboratively solve the conceptual problem in this context. Future work and implications for instruction are suggested.

physics.ed-ph↗

arXiv2023

AdaFuse: Adaptive Medical Image Fusion Based on Spatial-Frequential Cross Attention

Multi-modal medical image fusion is essential for the precise clinical diagnosis and surgical navigation since it can merge the complementary information in multi-modalities into a single image. The quality of the fused image depends on the extracted single modality features as well as the fusion rules for multi-modal information. Existing deep learning-based fusion methods can fully exploit the semantic features of each modality, they cannot distinguish the effective low and high frequency information of each modality and fuse them adaptively. To address this issue, we propose AdaFuse, in which multimodal image information is fused adaptively through frequency-guided attention mechanism based on Fourier transform. Specifically, we propose the cross-attention fusion (CAF) block, which adaptively fuses features of two modalities in the spatial and frequency domains by exchanging key and query values, and then calculates the cross-attention scores between the spatial and frequency features to further guide the spatial-frequential information fusion. The CAF block enhances the high-frequency features of the different modalities so that the details in the fused images can be retained. Moreover, we design a novel loss function composed of structure loss and content loss to preserve both low and high frequency information. Extensive comparison experiments on several datasets demonstrate that the proposed method outperforms state-of-the-art methods in terms of both visual quality and quantitative metrics. The ablation experiments also validate the effectiveness of the proposed loss and fusion strategy.

cs.CV↗

arXiv2023

Double Dirac cones in band structures of periodic Schrödinger operators

Dirac cones are conical singularities that occur near the degenerate points in band structures. Such singularities result in enormous unusual phenomena of the corresponding physical systems. This work investigates double Dirac cones that occur in the vicinity of a fourfold degenerate point in the band structures of certain operators. It is known that such degeneracy originates in the symmetries of the Hamiltonian. We use two dimensional periodic Schrödinger operators with novel designed symmetries as our prototype. First, we characterize admissible potentials, termed as super honeycomb lattice potentials. They are honeycomb lattices potentials with a key additional translation symmetry. It is rigorously justified that Schrödinger operators with such potentials almost guarantee the existence of double Dirac cones on the bands at the Γ point, the origin of the Brillouin zone. We further show that the additional translation symmetry is an indispensable ingredient by a perturbation analysis. Indeed, the double cones disappear if the additional translation symmetry is broken. Many numerical simulations are provided, which agree well with our analysis.

math-ph↗

arXiv2023

Optimal Regularized Online Allocation by Adaptive Re-Solving

This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially non-concave cumulative rewards, hard resource constraints, and a non-separable regularizer. Under a strategy of adaptively updating the resource constraints, the proposed framework only requests approximate solutions to the empirical dual problems up to a certain accuracy and yet delivers an optimal logarithmic regret under a locally second-order growth condition. Surprisingly, a delicate analysis of the dual objective function enables us to eliminate the notorious log-log factor in regret bound. The flexible framework renders renowned and computationally fast algorithms immediately applicable, e.g., dual stochastic gradient descent. Additionally, an infrequent re-solving scheme is proposed, which significantly reduces computational demands without compromising the optimal regret performance. A worst-case square-root regret lower bound is established if the resource constraints are not adaptively updated during dual optimization, which underscores the critical role of adaptive dual variable update. Comprehensive numerical experiments demonstrate the merits of the proposed algorithm framework.

cs.LG↗

arXiv2023

Multi-Agent Adversarial Training Using Diffusion Learning

This work focuses on adversarial learning over graphs. We propose a general adversarial training framework for multi-agent systems using diffusion learning. We analyze the convergence properties of the proposed scheme for convex optimization problems, and illustrate its enhanced robustness to adversarial attacks.

cs.LG↗

arXiv2023

Boosting Neural Networks to Decompile Optimized Binaries

Decompilation aims to transform a low-level program language (LPL) (eg., binary file) into its functionally-equivalent high-level program language (HPL) (e.g., C/C++). It is a core technology in software security, especially in vulnerability discovery and malware analysis. In recent years, with the successful application of neural machine translation (NMT) models in natural language processing (NLP), researchers have tried to build neural decompilers by borrowing the idea of NMT. They formulate the decompilation process as a translation problem between LPL and HPL, aiming to reduce the human cost required to develop decompilation tools and improve their generalizability. However, state-of-the-art learning-based decompilers do not cope well with compiler-optimized binaries. Since real-world binaries are mostly compiler-optimized, decompilers that do not consider optimized binaries have limited practical significance. In this paper, we propose a novel learning-based approach named NeurDP, that targets compiler-optimized binaries. NeurDP uses a graph neural network (GNN) model to convert LPL to an intermediate representation (IR), which bridges the gap between source code and optimized binary. We also design an Optimized Translation Unit (OTU) to split functions into smaller code fragments for better translation performance. Evaluation results on datasets containing various types of statements show that NeurDP can decompile optimized binaries with 45.21% higher accuracy than state-of-the-art neural decompilation frameworks.

cs.LG↗

arXiv2022

Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training

An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been proposed to improve the DNN accuracy but also consume massive memory in the training process with back-propagation. In this study, we propose the nested forward automatic differentiation (Forward-AD), specifically for the element-wise activation function for memory-efficient DNN training. We deploy nested Forward-AD in two widely-used deep learning frameworks, TensorFlow and PyTorch, which support the static and dynamic computation graph, respectively. Our evaluation shows that nested Forward-AD reduces the memory footprint by up to 1.97x than the baseline model and outperforms the recomputation by 20% under the same memory reduction ratio.

cs.LG↗

arXiv2022

Night-time Scene Parsing with a Large Real Dataset

Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions. In this work, we aim to address the night-time scene parsing (NTSP) problem, which has two main challenges: 1) labeled night-time data are scarce, and 2) over- and under-exposures may co-occur in the input night-time images and are not explicitly modeled in existing pipelines. To tackle the scarcity of night-time data, we collect a novel labeled dataset, named {\it NightCity}, of 4,297 real night-time images with ground truth pixel-level semantic annotations. To our knowledge, NightCity is the largest dataset for NTSP. In addition, we also propose an exposure-aware framework to address the NTSP problem through augmenting the segmentation process with explicitly learned exposure features. Extensive experiments show that training on NightCity can significantly improve NTSP performances and that our exposure-aware model outperforms the state-of-the-art methods, yielding top performances on our dataset as well as existing datasets.

cs.CV↗

arXiv2021

Semantics-Recovering Decompilation through Neural Machine Translation

Decompilation transforms low-level program languages (PL) (e.g., binary code) into high-level PLs (e.g., C/C++). It has been widely used when analysts perform security analysis on software (systems) whose source code is unavailable, such as vulnerability search and malware analysis. However, current decompilation tools usually need lots of experts' efforts, even for years, to generate the rules for decompilation, which also requires long-term maintenance as the syntax of high-level PL or low-level PL changes. Also, an ideal decompiler should concisely generate high-level PL with similar functionality to the source low-level PL and semantic information (e.g., meaningful variable names), just like human-written code. Unfortunately, existing manually-defined rule-based decompilation techniques only functionally restore the low-level PL to a similar high-level PL and are still powerless to recover semantic information. In this paper, we propose a novel neural decompilation approach to translate low-level PL into accurate and user-friendly high-level PL, effectively improving its readability and understandability. Furthermore, we implement the proposed approaches called SEAM. Evaluations on four real-world applications show that SEAM has an average accuracy of 94.41%, which is much better than prior neural machine translation (NMT) models. Finally, we evaluate the effectiveness of semantic information recovery through a questionnaire survey, and the average accuracy is 92.64%, which is comparable or superior to the state-of-the-art compilers.

cs.CR↗

arXiv2021

Online Network Utility Maximization: Algorithm, Competitive Analysis, and Applications

We consider an online version of the well-studied network utility maximization problem, where users arrive one by one and an operator makes irrevocable decisions for each user without knowing the details of future arrivals. We propose a threshold-based algorithm and analyze its worst-case performance. We prove that the competitive ratio of the proposed algorithm is linearly increasing in the number of links in a network and show this competitive analysis is tight. Extensive trace-driven simulations are conducted to demonstrate the performance of our proposed algorithm. In addition, since worst-case scenarios rarely occur in practice, we devise an adaptive implementation of our algorithm to improve its average-case performance and validate its effectiveness via simulations.

cs.DS↗

arXiv2021

Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation

In this paper, we propose a fully automatic system for generating comic books from videos without any human intervention. Given an input video along with its subtitles, our approach first extracts informative keyframes by analyzing the subtitles, and stylizes keyframes into comic-style images. Then, we propose a novel automatic multi-page layout framework, which can allocate the images across multiple pages and synthesize visually interesting layouts based on the rich semantics of the images (e.g., importance and inter-image relation). Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios. Our method is able to vary balloon shapes and word sizes in balloons in response to different emotions, leading to more enriched reading experience. Once the balloons are generated, they are placed adjacent to their corresponding speakers via speaker detection. Our results show that our method, without requiring any user inputs, can generate high-quality comic pages with visually rich layouts and balloons. Our user studies also demonstrate that users prefer our generated results over those by state-of-the-art comic generation systems.

cs.CV↗

arXiv2020

Optimal Online Algorithms for One-Way Trading and Online Knapsack Problems: A Unified Competitive Analysis

We study two canonical online optimization problems under capacity/budget constraints: the fractional one-way trading problem (OTP) and the integral online knapsack problem (OKP) under an infinitesimal assumption. Under the competitive analysis framework, it is well-known that both problems have the same optimal competitive ratio. However, these two problems are investigated by distinct approaches under separate contexts in the literature. There is a gap in understanding the connection between these two problems and the nature of their online algorithm design. This paper provides a unified framework for the online algorithm design, analysis and optimality proof for both problems. We find that the infinitesimal assumption of the OKP is the key that connects the OTP in the analysis of online algorithms and the construction of worst-case instances. With this unified understanding, our framework shows its potential for analyzing other extensions of OKP and OTP in a more systematic manner.

cs.DS↗