arXiv subjects

Zhengyang Ji

Publications and source records attributed to Zhengyang Ji.

5 recordsLinked to original sources

arXiv2026

Hausdorff--Choquet Angular Spaces and Weak-Type $(1,1)$ Bounds for Rough Maximal Operators

In the present paper, we consider the maximal operator \[ \mathcal M_Ωf(x) := \sup_{r>0}\frac{1}{r^n} \int_{|y|<r} |f(x-y)| \left| Ω\!\left(\frac{y}{|y|}\right) \right|\,dy. \] A longstanding open conjecture raised by E.~M.~Stein asks whether the maximal operator $\mathcal M_Ω$ is of weak type $(1,1)$ when $Ω$ is merely in $L^1(\mathbb S^{n-1})$. We partially settle this problem by proving weak type $(1,1)$ bounds of $\mathcal M_Ω$ with kernel $Ω\in\mathcal X(\mathbb S^{n-1})$, yielding a significant improvement over the work of M.~Christ and Rubio de Francia. Here $\mathcal X(\mathbb S^{n-1})$ is the space related to the Hausdorff--Choquet angular space and $$ L\log^+\!L(\mathbb S^{n-1}) \subsetneq \mathcal X(\mathbb S^{n-1})\subset L^1(\mathbb S^{n-1}). $$ Finally, for the general Hausdorff--Choquet scale $\mathcal H\mathcal C_α$, we show that $α=(n-1)/2$ is the sharp exponent for uniform weak type $(1,1)$ estimates.

math.CA↗

arXiv2026

On the relationship between block spaces and Orlicz spaces

Let $1 -1$. Let $(X,d,μ)$ be an $s$-Ahlfors-regular quasi-metric measure space. Suppose that $B^{0,v}_q(X)$ is the block space which consists of all functions that admit a decomposition into $q$-blocks supported on balls. In this paper, we study the relationship between the block space $B^{0,v}_q(X)$ and the Orlicz-type space $L(\log^+\!\!L)^{1+v}(X)$. More precisely, we show that the block space $B_q^{0,v}(X)$ is a proper subspace of the Orlicz space $L(\log^+\!\!L)^{1+v}(X)$ for any fixed $1 -1$. Namely, $$B_q^{0,v}(X)\subsetneq L(\log^+\!\!L)^{1+v}(X),$$ which gives a confirmed answer to a longstanding open problem concerning the relationship between block spaces and Orlicz-type spaces on the unit sphere $\mathbb S^{n-1}$. We further show that $L(\log^+\!\!L)^{1+v}(X)$ is the smallest Orlicz-type space containing $B^{0,v}_{q}(X)$. We also introduce a generalized block space $\mathscr B_q^{0,v}(X)$ that depends only on the measure structure and show that this space is equivalent to the Orlicz space $L(\log^+\!\!L)^{1+v}(X)$ when $μ(X)<\infty$. Finally, we consider two special cases that further clarify the roles of the parameter $q$ and the logarithmic weight.

math.CA↗

arXiv2025

Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluation

Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases. These biases often manifest as unintended associations between neutral concepts and sensitive human attributes, leading to disparate model behaviors across demographic groups. While existing studies primarily focus on detecting and quantifying such biases, they offer limited insight into the underlying mechanisms within the models. To address this gap, we propose an explanatory framework that combines information flow analysis with multi-round dialogue evaluation, aiming to understand the origin of social bias from the perspective of imbalanced internal information utilization. Specifically, we first identify high-contribution image tokens involved in the model's reasoning process for neutral questions via information flow analysis. Then, we design a multi-turn dialogue mechanism to evaluate the extent to which these key tokens encode sensitive information. Extensive experiments reveal that LVLMs exhibit systematic disparities in information usage when processing images of different demographic groups, suggesting that social bias is deeply rooted in the model's internal reasoning dynamics. Furthermore, we complement our findings from a textual modality perspective, showing that the model's semantic representations already display biased proximity patterns, thereby offering a cross-modal explanation of bias formation.

cs.AI↗

arXiv2025

BioD2C: A Dual-level Semantic Consistency Constraint Framework for Biomedical VQA

Biomedical visual question answering (VQA) has been widely studied and has demonstrated significant application value and potential in fields such as assistive medical diagnosis. Despite their success, current biomedical VQA models perform multimodal information interaction only at the model level within large language models (LLMs), leading to suboptimal multimodal semantic alignment when dealing with complex tasks. To address this issue, we propose BioD2C: a novel Dual-level Semantic Consistency Constraint Framework for Biomedical VQA, which achieves dual-level semantic interaction alignment at both the model and feature levels, enabling the model to adaptively learn visual features based on the question. Specifically, we firstly integrate textual features into visual features via an image-text fusion mechanism as feature-level semantic interaction, obtaining visual features conditioned on the given text; and then introduce a text-queue-based cross-modal soft semantic loss function to further align the image semantics with the question semantics. Specifically, in this work, we establish a new dataset, BioVGQ, to address inherent biases in prior datasets by filtering manually-altered images and aligning question-answer pairs with multimodal context, and train our model on this dataset. Extensive experimental results demonstrate that BioD2C achieves state-of-the-art (SOTA) performance across multiple downstream datasets, showcasing its robustness, generalizability, and potential to advance biomedical VQA research.

cs.CV↗

arXiv2025

Adaptive H&E-IHC information fusion staining framework based on feature extra

Immunohistochemistry (IHC) staining plays a significant role in the evaluation of diseases such as breast cancer. The H&E-to-IHC transformation based on generative models provides a simple and cost-effective method for obtaining IHC images. Although previous models can perform digital coloring well, they still suffer from (i) coloring only through the pixel features that are not prominent in HE, which is easy to cause information loss in the coloring process; (ii) The lack of pixel-perfect H&E-IHC groundtruth pairs poses a challenge to the classical L1 loss.To address the above challenges, we propose an adaptive information enhanced coloring framework based on feature extractors. We first propose the VMFE module to effectively extract the color information features using multi-scale feature extraction and wavelet transform convolution, while combining the shared decoder for feature fusion. The high-performance dual feature extractor of H&E-IHC is trained by contrastive learning, which can effectively perform feature alignment of HE-IHC in high latitude space. At the same time, the trained feature encoder is used to enhance the features and adaptively adjust the loss in the HE section staining process to solve the problems related to unclear and asymmetric information. We have tested on different datasets and achieved excellent performance.Our code is available at https://github.com/babyinsunshine/CEFF

cs.CV↗