papers

Publications (41)

cs.CV2025

Learning Representation and Synergy Invariances: A Povable Framework for Generalized Multimodal Face Anti-Spoofing

Xun Lin, Shuai Wang, Yi Yu +6

Multimodal Face Anti-Spoofing (FAS) methods, which integrate multiple visual modalities, often suffer even more severe performance degradation than unimodal FAS when deployed in un…

cs.AI2025

Dynamic Analysis and Adaptive Discriminator for Fake News Detection

Xinqi Su, Zitong Yu, Yawen Cui +7

In current web environment, fake news spreads rapidly across online social networks, posing serious threats to society. Existing multimodal fake news detection methods can generall…

cs.LG2019

A Distributed Approach towards Discriminative Distance Metric Learning

Jun Li, Xun Lin, Xiaoguang Rui +2

Distance metric learning is successful in discovering intrinsic relations in data. However, most algorithms are computationally demanding when the problem size becomes large. In th…

math.AG2024

Fully faithful functors, skyscraper sheaves, and birational equivalence

Chunyi Li, Xun Lin, Xiaolei Zhao

Let and be two smooth projective varieties such that there is a fully faithful exact functor from to . We show that and

cs.CV2025

FaceShield: Explainable Face Anti-Spoofing with Multimodal Large Language Models

Hongyang Wang, Yichen Shi, Zhuofu Tao +7

Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking…

cs.CV2025

TopoTTA: Topology-Enhanced Test-Time Adaptation for Tubular Structure Segmentation

Jiale Zhou, Wenhan Wang, Shikun Li +6

Tubular structure segmentation (TSS) is important for various applications, such as hemodynamic analysis and route navigation. Despite significant progress in TSS, domain shifts re…

cs.CV2026

VISTA: Variance-Gated Inter-Sequence Test-Time Adaptation for Multi-Sequence MRI Segmentation

Zhipeng Deng, Jiale Zhou, Wenhan Jiang +4

Deploying multi-sequence magnetic resonance imaging (MRI) segmentation models to new clinical environments is challenging due to variations in scanners and acquisition protocols. A…

cs.CR2026

Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks

Yi Yu, Qixin Zhang, Shuhan Ye +6

Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure, yet most adversarial attacks change intensities or event counts instead of timing. We st…

math.AG2025

Infinitesimal Torelli problems for special Gushel-Mukai and related Fano threefolds: Hodge theoretical and categorical perspectives

Xun Lin, Shizhuo Zhang, Zheng Zhang

We investigate infinitesimal Torelli problems for some of the Fano threefolds of the following two types: (a) those which can be described as zero loci of sections of vector bundle…

cs.CV2024

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models

Jing Yang, Runping Xi, Yingxin Lai +2

Diffusion-based personalized visual content generation technologies have achieved significant breakthroughs, allowing for the creation of specific objects by just learning from a f…

cs.CV2026

AV-Master: Dual-Path Comprehensive Perception Makes Better Audio-Visual Question Answering

Jiayu Zhang, Shuo Ye, Qilang Ye +3

Audio-Visual Question Answering (AVQA) requires models to effectively utilize both visual and auditory modalities to answer complex and diverse questions about audio-visual scenes.…

cs.LG2025

Transferable Adversarial Attacks on SAM and Its Downstream Models

Song Xia, Wenhan Yang, Yi Yu +4

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical…

math.AG2021

Noncommutative Hodge conjecture

Xun Lin

The paper provides a version of the rational Hodge conjecture for $\3\dg$ categories. The noncommutative Hodge conjecture is equivalent to the version proposed in \cite{perry2020in…

math.AG2021

Some remarks of Hochschild homology and semi-orthogonal decompositions

Xun Lin

Given a nontrivial semi-orthogonal decomposition $\Perf(\X)=\langle \mathcal{A},\mathcal{B}\rangle$, and assume that the base locus of $ω_{\X}$ is a proper closed subset, it was p…

cs.CV2026

VoxShield: Protecting 3D Medical Datasets from Unauthorized Training via Frequency-Aware Inter-Slice Disruption

Xinyao Liu, Zhipeng Deng, Wenhan Jiang +4

The release of public 3D medical image segmentation (MIS) datasets accelerates clinical research but simultaneously heightens risks of unauthorized AI model training. While Unlearn…

cs.CV2025

StegaVAR: Privacy-Preserving Video Action Recognition via Steganographic Domain Analysis

Lixin Chen, Chaomeng Chen, Jiale Zhou +2

Despite the rapid progress of deep learning in video action recognition (VAR) in recent years, privacy leakage in videos remains a critical concern. Current state-of-the-art privac…

cs.CV2025

DADM: Dual Alignment of Domain and Modality for Face Anti-spoofing

Jingyi Yang, Xun Lin, Zitong Yu +5

With the availability of diverse sensor modalities (i.e., RGB, Depth, Infrared) and the success of multi-modal learning, multi-modal face anti-spoofing (FAS) has emerged as a promi…

math.AG2024

Serre algebra, matrix factorization and categorical Torelli theorem for hypersurfaces

Xun Lin, Shizhuo Zhang

Let be a smooth Fano variety. We attach a bi-graded associative algebra $\mathrm{HS}(\mathcal{K}u(X))=\bigoplus_{i,j\in \mathbb{Z}} \mathrm{Hom}(\mathrm{Id},S_{\mathcal{K}u(X)}…

math.AG2021

Indecomposability of the bounded derived categories of Brill-Noether varieties

Xun Lin, Chenglong Yu

We prove that the bounded derived category of coherent sheaves of the Brill-Noether variety that parametrizing linear series of degree and dimension on a gen…

math.AG2026

Semiorthogonal indecomposability for Hilbert schemes of points on integral locally planar curves

Qingyuan Jiang, Xun Lin

Let be an integral projective curve of arithmetic genus with locally planar singularities over an algebraically closed field. We prove that for every , bot…

cs.CV2026

SVC 2026: the Second Multimodal Deception Detection Challenge and the First Domain Generalized Remote Physiological Measurement Challenge

Dongliang Zhu, Zhiyi Niu, Bo Zhao +14

Subtle visual signals, although difficult to perceive with the naked eye, contain important information that can reveal hidden patterns in visual data. These signals play a key rol…

cs.CV2024

EPE-P: Evidence-based Parameter-efficient Prompting for Multimodal Learning with Missing Modalities

Zhe Chen, Xun Lin, Yawen Cui +1

Missing modalities are a common challenge in real-world multimodal learning scenarios, occurring during both training and testing. Existing methods for managing missing modalities…

math.AG2021

On nonexistence of semi-orthogonal decompositions in algebraic geometry

Xun Lin

The nonexistence of semi-orthogonal decompositions in algebraic geometry is known to be governed by the base locus of the canonical bundle. We study another locus, namely the inter…

cs.CV2026

Purify then Guide: Rethinking Domain Generalization for Multimodal Face Anti-Spoofing

Yingjie Ma, Xun Lin, Zitong Yu +7

Face Anti-Spoofing (FAS) is essential for the security of facial recognition systems in diverse scenarios such as payment processing and surveillance. Current multimodal FAS method…

math.AG2024

IVHS via Kuznetsov components and categorical Torelli theorems for weighted hypersurfaces

Xun Lin, Jørgen Vold Rennemo, Shizhuo Zhang

We study the categorical Torelli theorem for smooth (weighted) hypersurfaces in (weighted) projective spaces via the Hochschild--Serre algebra of its Kuznetsov component. In the fi…

cs.CV2025

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger

Yi Yu, Song Xia, Xun Lin +4

No-Reference Image Quality Assessment (NR-IQA), responsible for assessing the quality of a single input image without using any reference, plays a critical role in evaluating and o…

cs.CV2024

Exposing Image Splicing Traces in Scientific Publications via Uncertainty-guided Refinement

Xun Lin, Wenzhong Tang, Haoran Wang +4

Recently, a surge in scientific publications suspected of image manipulation has led to numerous retractions, bringing the issue of image integrity into sharp focus. Although resea…

cs.CV2024

BIG-MoE: Bypass Isolated Gating MoE for Generalized Multimodal Face Anti-Spoofing

Yingjie Ma, Zitong Yu, Xun Lin +2

In the domain of facial recognition security, multimodal Face Anti-Spoofing (FAS) is essential for countering presentation attacks. However, existing technologies encounter challen…

cs.CV2024

Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing

Xun Lin, Shuai Wang, Rizhao Cai +5

Face Anti-Spoofing (FAS) is crucial for securing face recognition systems against presentation attacks. With advancements in sensor manufacture and multi-modal learning techniques,…

cs.CL2026

MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education

Qian Wu, Xinrong Zhou, Zizhan Ma +8

Large Language Models (LLMs) show promise for medical education, but most existing systems focus on localized interactions such as question answering or single-turn feedback, rathe…

cs.AI2026

Multimodal Mixture-of-Experts with Retrieval Augmentation for Protein Active Site Identification

Jiayang Wu, Jiale Zhou, Rubo Wang +5

Accurate identification of protein active sites at the residue level is crucial for understanding protein function and advancing drug discovery. However, current methods face two c…

cs.CR2025

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation

Yi Yu, Song Xia, Xun Lin +5

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these exa…

cs.CV2025

SVC 2025: the First Multimodal Deception Detection Challenge

Xun Lin, Xiaobao Guo, Taorui Wang +5

Deception detection is a critical task in real-world applications such as security screening, fraud prevention, and credibility assessment. While deep learning methods have shown p…

cs.CV2025

AdaMHF: Adaptive Multimodal Hierarchical Fusion for Survival Prediction

Shuaiyu Zhang, Xun Lin, Rongxiang Zhang +5

The integration of pathologic images and genomic data for survival analysis has gained increasing attention with advances in multimodal learning. However, current methods often ign…

eess.IV2024

Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations

Xun Lin, Yi Yu, Song Xia +8

The widespread availability of publicly accessible medical images has significantly propelled advancements in various research and clinical fields. Nonetheless, concerns regarding…

cs.CV2026

StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting

Guoqing Ma, Xun Lin, Hui Ma +6

Most existing Face Forgery Detection (FFD) models assume access to raw face images. In practice, under a client-server framework, private facial data may be intercepted during tran…

math.AG2024

Three approaches to a categorical Torelli theorem for cubic threefolds of non-Eckardt type via the equivariant Kuznetsov components

Sebastian Casalaina-Martin, Xianyu Hu, Xun Lin +2

Let be a cubic threefold with a non-Eckardt type involution . Our first main result is that the -equivariant category of the Kuznetsov component $\mathcal{K}u_{\mathbb{…

math.AG2023

Infinitesimal categorical Torelli theorems for Fano threefolds

Augustinas Jacovskis, Xun Lin, Zhiyu Liu +1

Let be a smooth Fano variety and the Kuznetsov component. Torelli theorems for says that it is uniquely determined by a polarized abelian va…

math.AG2024

Kuznetsov's Fano threefold conjecture via Hochschild-Serre algebra

Xun Lin, Shizhuo Zhang

Let be a smooth quartic double solid regarded as a degree 4 hypersurface of the weighted projective space . We study the multiplication of Hochschild-Ser…

cs.CV2025

PA-FAS: Towards Interpretable and Generalizable Multimodal Face Anti-Spoofing via Path-Augmented Reinforcement Learning

Yingjie Ma, Xun Lin, Yong Xu +2

Face anti-spoofing (FAS) has recently advanced in multimodal fusion, cross-domain generalization, and interpretability. With large language models and reinforcement learning (RL),…

math.AG2024

Categorical Torelli theorems for Gushel-Mukai threefolds

Augustinas Jacovskis, Xun Lin, Zhiyu Liu +1

We show that a general ordinary Gushel-Mukai(GM) threefold is reconstructed from the Kuznetsov component together with an extra data coming from tautological…