Searcharxiv⌕ Search

arXiv subjects

Xiaoyan Zhang

Publications and source records attributed to Xiaoyan Zhang.

At least 37 records · Page 2Linked to original sources
arXiv2026

MFP3D: Monocular Food Portion Estimation Leveraging 3D Point Clouds

Food portion estimation is crucial for monitoring health and tracking dietary intake. Image-based dietary assessment, which involves analyzing eating occasion images using computer vision techniques, is increasingly replacing traditional methods such as 24-hour recalls. However, accurately estimating the nutritional content from images remains challenging due to the loss of 3D information when projecting to the 2D image plane. Existing portion estimation methods are challenging to deploy in real-world scenarios due to their reliance on specific requirements, such as physical reference objects, high-quality depth information, or multi-view images and videos. In this paper, we introduce MFP3D, a new framework for accurate food portion estimation using only a single monocular image. Specifically, MFP3D consists of three key modules: (1) a 3D Reconstruction Module that generates a 3D point cloud representation of the food from the 2D image, (2) a Feature Extraction Module that extracts and concatenates features from both the 3D point cloud and the 2D RGB image, and (3) a Portion Regression Module that employs a deep regression model to estimate the food's volume and energy content based on the extracted features. Our MFP3D is evaluated on MetaFood3D dataset, demonstrating its significant improvement in accurate portion estimation over existing methods.

cs.CV↗
arXiv2026

SpatiaLQA: A Benchmark for Evaluating Spatial Logical Reasoning in Vision-Language Models

Vision-Language Models (VLMs) have been increasingly applied in real-world scenarios due to their outstanding understanding and reasoning capabilities. Although VLMs have already demonstrated impressive capabilities in common visual question answering and logical reasoning, they still lack the ability to make reasonable decisions in complex real-world environments. We define this ability as spatial logical reasoning, which not only requires understanding the spatial relationships among objects in complex scenes, but also the logical dependencies between steps in multi-step tasks. To bridge this gap, we introduce Spatial Logical Question Answering (SpatiaLQA), a benchmark designed to evaluate the spatial logical reasoning capabilities of VLMs. SpatiaLQA consists of 9,605 question answer pairs derived from 241 real-world indoor scenes. We conduct extensive experiments on 41 mainstream VLMs, and the results show that even the most advanced models still struggle with spatial logical reasoning. To address this issue, we propose a method called recursive scene graph assisted reasoning, which leverages visual foundation models to progressively decompose complex scenes into task-relevant scene graphs, thereby enhancing the spatial logical reasoning ability of VLMs, outperforming all previous methods. Code and dataset are available at https://github.com/xieyc99/SpatiaLQA.

cs.CV↗
arXiv2026

Dimensionality and randomness

Arranging the bits of a random string or real into k columns of a two-dimensional array or higher dimensional structure is typically accompanied with loss in the Kolmogorov complexity of the columns, which depends on k. We quantify and characterize this phenomenon for arrays and trees and its relationship to negligible classes.

math.LO↗
arXiv2026

SIGMA: Selective-Interleaved Generation with Multi-Attribute Tokens

Recent unified models such as Bagel demonstrate that paired image-edit data can effectively align multiple visual tasks within a single diffusion transformer. However, these models remain limited to single-condition inputs and lack the flexibility needed to synthesize results from multiple heterogeneous sources. We present SIGMA (Selective-Interleaved Generation with Multi-Attribute Tokens), a unified post-training framework that enables interleaved multi-condition generation within diffusion transformers. SIGMA introduces selective multi-attribute tokens, including style, content, subject, and identity tokens, which allow the model to interpret and compose multiple visual conditions in an interleaved text-image sequence. Through post-training on the Bagel unified backbone with 700K interleaved examples, SIGMA supports compositional editing, selective attribute transfer, and fine-grained multimodal alignment. Extensive experiments show that SIGMA improves controllability, cross-condition consistency, and visual quality across diverse editing and generation tasks, with substantial gains over Bagel on compositional tasks.

cs.CV↗
arXiv2025

Beyond the Hype: A Large-Scale Empirical Analysis of On-Chain Transactions in NFT Scams

Non-fungible tokens (NFTs) serve as a representative form of digital asset ownership and have attracted numerous investors, creators, and tech enthusiasts in recent years. However, related fraud activities, especially phishing scams, have caused significant property losses. There are many graph analysis methods to detect malicious scam incidents, but no research on the transaction patterns of the NFT scams. Therefore, to fill this gap, we are the first to systematically explore NFT phishing frauds through graph analysis, aiming to comprehensively investigate the characteristics and patterns of NFT phishing frauds on the transaction graph. During the research process, we collect transaction records, log data, and security reports related to NFT phishing incidents published on multiple platforms. After collecting, sanitizing, and unifying the data, we construct a transaction graph and analyze the distribution, transaction features, and interaction patterns of NFT phishing scams. We find that normal transactions on the blockchain accounted for 96.71% of all transactions. Although phishing-related accounts accounted for only 0.94% of the total accounts, they appeared in 8.36% of the transaction scenarios, and their interaction probability with normal accounts is significantly higher in large-scale transaction networks. Moreover, NFT phishing scammers often carry out fraud in a collective manner, targeting specific accounts, tend to interact with victims through multiple token standards, have shorter transaction cycles than normal transactions, and involve more multi-party transactions. This study reveals the core behavioral features of NFT phishing scams, providing important references for the detection and prevention of NFT phishing scams in the future.

cs.CR↗
arXiv2025

Non-asymptotic Error Analysis of Explicit Modified Euler Methods for Superlinear and Non-contractive SODEs

A family of explicit modified Euler methods (MEMs) is constructed for long-time approximations of super-linear SODEs driven by multiplicative noise. The proposed schemes can preserve the same Lyapunov structure as the continuous problems. Under a non-contractive condition, we establish a non-asymptotic error bound between the law of the numerical approximation and the target distribution in Wasserstein-1 ($\mathcal{W}_1$) distance through a time-independent weak convergence rate for the proposed schemes. As a by-product of this weak error estimate, we obtain an $\mathcal{O}(τ|\ln τ|)$ convergence rate between the exact and numerical invariant measures.

math.NA↗
arXiv2025

StyDeco: Unsupervised Style Transfer with Distilling Priors and Semantic Decoupling

Diffusion models have emerged as the dominant paradigm for style transfer, but their text-driven mechanism is hindered by a core limitation: it treats textual descriptions as uniform, monolithic guidance. This limitation overlooks the semantic gap between the non-spatial nature of textual descriptions and the spatially-aware attributes of visual style, often leading to the loss of semantic structure and fine-grained details during stylization. In this paper, we propose StyDeco, an unsupervised framework that resolves this limitation by learning text representations specifically tailored for the style transfer task. Our framework first employs Prior-Guided Data Distillation (PGD), a strategy designed to distill stylistic knowledge without human supervision. It leverages a powerful frozen generative model to automatically synthesize pseudo-paired data. Subsequently, we introduce Contrastive Semantic Decoupling (CSD), a task-specific objective that adapts a text encoder using domain-specific weights. CSD performs a two-class clustering in the semantic space, encouraging source and target representations to form distinct clusters. Extensive experiments on three classic benchmarks demonstrate that our framework outperforms several existing approaches in both stylistic fidelity and structural preservation, highlighting its effectiveness in style transfer with semantic preservation. In addition, our framework supports a unique de-stylization process, further demonstrating its extensibility. Our code is vailable at https://github.com/QuanjianSong/StyDeco.

cs.CV↗
arXiv2025

Computable one-way functions on the reals

A major open problem in computational complexity is the existence of a one-way function, namely a function from strings to strings which is computationally easy to compute but hard to invert. Levin (2023) formulated the notion of one-way functions from reals (infinite bit-sequences) to reals in terms of computability, and asked whether partial computable one-way functions exist. We give a strong positive answer using the hardness of the halting problem and exhibiting a total computable one-way function.

cs.CC↗
arXiv2025

Dataset Ownership Verification for Pre-trained Masked Models

High-quality open-source datasets have emerged as a pivotal catalyst driving the swift advancement of deep learning, while facing the looming threat of potential exploitation. Protecting these datasets is of paramount importance for the interests of their owners. The verification of dataset ownership has evolved into a crucial approach in this domain; however, existing verification techniques are predominantly tailored to supervised models and contrastive pre-trained models, rendering them ill-suited for direct application to the increasingly prevalent masked models. In this work, we introduce the inaugural methodology addressing this critical, yet unresolved challenge, termed Dataset Ownership Verification for Masked Modeling (DOV4MM). The central objective is to ascertain whether a suspicious black-box model has been pre-trained on a particular unlabeled dataset, thereby assisting dataset owners in safeguarding their rights. DOV4MM is grounded in our empirical observation that when a model is pre-trained on the target dataset, the difficulty of reconstructing masked information within the embedding space exhibits a marked contrast to models not pre-trained on that dataset. We validated the efficacy of DOV4MM through ten masked image models on ImageNet-1K and four masked language models on WikiText-103. The results demonstrate that DOV4MM rejects the null hypothesis, with a $p$-value considerably below 0.05, surpassing all prior approaches. Code is available at https://github.com/xieyc99/DOV4MM.

cs.CV↗
arXiv2025

Compression of enumerations and gain

We study the compressibility of enumerations in the context of Kolmogorov complexity, focusing on strong and weak forms of compression and their gain: the amount of auxiliary information embedded in the compressed enumeration. The existence of strong compression and weak gainless compression is shown for any computably enumerable (c.e.) set. The density problem of c.e. sets with respect to their prefix complexity is reduced to the question of whether every c.e. set is well-compressible, which we study via enumeration games.

cs.CL↗
arXiv2025

Path Extendable Tournaments

A digraph $D$ is called \emph{path extendable} if for every nonhamiltonian (directed) path $P$ in $D$, there exists another path $P^\prime$ with the same initial and terminal vertices as $P$, and $V(P^\prime) = V (P)\cup \{w\}$ for a vertex $w \in V(D)\setminus V(P)$. Hence, path extendability implies paths of continuous lengths between every vertex pair. In earlier works of C. Thomassen and K. Zhang, it was shown that the condition of small $i(T)$ or positive $π_2(T)$ implies paths of continuous lengths between every vertex pair in a tournament $T$, where $i(T)$ is the irregularity of $T$ and $π_2(T)$ denotes for the minimum number of paths of length $2$ from $u$ to $v$ among all vertex pairs $\{u,v\}$. Motivated by these results, we study sufficient conditions in terms of $i(T)$ and $π_2(T)$ that guarantee a tournament $T$ is path extendable. We prove that (1) a tournament $T$ is path extendable if $i(T)< 2π_2(T)-(|T|+8)/6$, and (2) a tournament $T$ is path extendable if $π_2(T) > (7|T|-10)/36$. As an application, we deduce that almost all random tournaments are path extendable.

math.CO↗
arXiv2025

Long-Tailed Continual Learning For Visual Food Recognition

Deep learning-based food recognition has made significant progress in predicting food types from eating occasion images. However, two key challenges hinder real-world deployment: (1) continuously learning new food classes without forgetting previously learned ones, and (2) handling the long-tailed distribution of food images, where a few common classes and many more rare classes. To address these, food recognition methods should focus on long-tailed continual learning. In this work, We introduce a dataset that encompasses 186 American foods along with comprehensive annotations. We also introduce three new benchmark datasets, VFN186-LT, VFN186-INSULIN and VFN186-T2D, which reflect real-world food consumption for healthy populations, insulin takers and individuals with type 2 diabetes without taking insulin. We propose a novel end-to-end framework that improves the generalization ability for instance-rare food classes using a knowledge distillation-based predictor to avoid misalignment of representation during continual learning. Additionally, we introduce an augmentation technique by integrating class-activation-map (CAM) and CutMix to improve generalization on instance-rare food classes. Our method, evaluated on Food101-LT, VFN-LT, VFN186-LT, VFN186-INSULIN, and VFN186-T2DM, shows significant improvements over existing methods. An ablation study highlights further performance enhancements, demonstrating its potential for real-world food recognition applications.

cs.CV↗
arXiv2025

Ground state and multiple normalized solutions of quasilinear Schrödinger equations in the $L^2$-supercritical case and the Sobolev critical case

This paper is devoted to studying the existence of normalized solutions for the following quasilinear Schrödinger equation \begin{equation*} \begin{aligned} -Δu-uΔu^2 +λu=|u|^{p-2}u \quad\mathrm{in}\ \mathbb{R}^{N}, \end{aligned} \end{equation*} where $N=3,4$, $λ$ appears as a Lagrange multiplier and $p \in (4+\frac{4}{N},2\cdot2^*]$. The solutions correspond to critical points of the energy functional subject to the $L^2$-norm constraint $\int_{\mathbb{R}^N}|u|^2dx=a^2>0$. In the Sobolev critical case $p=2\cdot 2^*$, the energy functional has no critical point. As for $L^2$-supercritical case $p \in (4+\frac{4}{N},2\cdot2^*)$: on the one hand, taking into account Pohozaev manifold and perturbation method, we obtain the existence of ground state normalized solutions for the non-radial case; on the other hand, we get the existence of infinitely many normalized solutions in $H^1_r(\mathbb{R}^N)$. Moreover, our results cover several relevant existing results. And in the end, we get the asymptotic properties of energy as $a$ tends to $+\infty$ and $a$ tends to $0^+$.

math.AP↗
arXiv2025

Collision-resistant hash-shuffles on the reals

Oneway real functions are effective maps on positive-measure sets of reals that preserve randomness and have no effective probabilistic inversions. We construct a oneway real function which is collision-resistant: the probability of effectively producing distinct reals with the same image is zero, and each real has uncountable inverse image.

math.LO↗
arXiv2024

Nuclear mass table in deformed relativistic Hartree-Bogoliubov theory in continuum, II: Even-$Z$ nuclei

The mass table in the deformed relativistic Hartree-Bogoliubov theory in continuum (DRHBc) with the PC-PK1 density functional has been established for even-$Z$ nuclei with $8\le Z\le120$, extended from the previous work for even-even nuclei [Zhang $\it{et.~al.}$ (DRHBc Mass Table Collaboration), At. Data Nucl. Data Tables 144, 101488 (2022)]. The calculated binding energies, two-nucleon and one-neutron separation energies, root-mean-square (rms) radii of neutron, proton, matter, and charge distributions, quadrupole deformations, and neutron and proton Fermi surfaces are tabulated and compared with available experimental data. A total of 4829 even-$Z$ nuclei are predicted to be bound, with an rms deviation of 1.477 MeV from the 1244 mass data. Good agreement with the available experimental odd-even mass differences, $α$ decay energies, and charge radii is also achieved. The description accuracy for nuclear masses and nucleon separation energies as well as the prediction for drip lines is compared with the results obtained from other relativistic and nonrelativistic density functional. The comparison shows that the DRHBc theory with PC-PK1 provides an excellent microscopic description for the masses of even-$Z$ nuclei. The systematics of the nucleon separation energies, odd-even mass differences, pairing energies, two-nucleon gaps, $α$ decay energies, rms radii, quadrupole deformations, potential energy curves, neutron density distributions, and neutron mean-field potentials are discussed.

nucl-th↗
arXiv2024

Approximation Algorithm of Minimum All-Ones Problem for Arbitrary Graphs

Let $G=(V, E)$ be a graph and let each vertex of $G$ has a lamp and a button. Each button can be of $σ^+$-type or $σ$-type. Assume that initially some lamps are on and others are off. The button on vertex $x$ is of $σ^+$-type ($σ$-type, respectively) if pressing the button changes the lamp states on $x$ and on its neighbors in $G$ (the lamp states on the neighbors of $x$ only, respectively). Assume that there is a set $X\subseteq V$ such that pressing buttons on vertices of $X$ lights all lamps on vertices of $G$. In particular, it is known to hold when initially all lamps are off and all buttons are of $σ^+$-type. Finding such a set $X$ of the smallest size is NP-hard even if initially all lamps are off and all buttons are of $σ^+$-type. Using a linear algebraic approach we design a polynomial-time approximation algorithm for the problem such that for the set $X$ constructed by the algorithm, we have $|X|\le \min\{r,(|V|+{\rm opt})/2\},$ where $r$ is the rank of a (modified) adjacent matrix of $G$ and ${\rm opt}$ is the size of an optimal solution to the problem. To the best of our knowledge, this is the first polynomial-time approximation algorithm for the problem with a nontrivial approximation guarantee.

cs.DS↗
arXiv2024

Growth and irreducibility in path-incompressible trees

We study effective randomness-preserving transformations of path-incompressible trees. Some path-incompressible trees with infinitely many paths do not compute perfect path-random trees with computable oracle-use. Sparse perfect path-incompressible trees can be effectively densified, almost surely. We characterize the branching density of path-random trees.

math.CO↗