Donglin Di

Can Large Language Models Anticipate Behavioral Responses to Social Policies? A Case of Pension Enrollment Prediction among China's Flexible Workers

Yumiao Li, Peixin Liu, Donglin Di, Chen Li et autres

Assessing the impacts of social policy changes is a widely acknowledged challenge for policymakers. Econometric methods can be unreliable when extrapolating to hypothetical scenarios, while field pilot programs are highly costly. In this paper, we propose using large language models (LLMs) as …

ADNet: A multi-domain benchmark for anomaly detection across 380 real-world categories

Hai Ling, Jia Guo, Zhulin Tao, Donglin Di et autres

Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range of categories, limiting the evaluation of cross-context generalization and scalability. We introduce ADNet, a large-scale, multi-domain benchmark …

us, cn, ca, au (code pays fourni par la source)

Unified multimodal computational pathology with missing-modality robustness via Riemannian learning

Guang Yang, Mingcheng Qu, Donglin Di, Kai Yi et autres

Recent advances in multimodal computational pathology (CPath) have enabled the integration of pathological and molecular data. However, existing studies often rely on a single omics modality (e.g., DNA or transcriptomics), overlooking cross-layer biological dependencies and failing to effectively handle the missing-modality challenge …

cn, gb, us, au (code pays fourni par la source)

STAG: Biologically guided spatial transcriptomics prediction via hypergraph learning

Mingcheng Qu, Yuchuan Zhao, Guang Yang, Donglin Di et autres

Spatial transcriptomics (ST) enables spatially resolved gene expression profiling within intact tissue sections. However, its widespread adoption is constrained by the high cost and low throughput of current sequencing-based protocols. This has motivated growing interest in computationally predicting gene expression directly from …

cn, au (code pays fourni par la source)

ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection

Ningning Han, Lei Fan, Jia Guo, Yunkang Cao et autres

The deployment of Industrial Anomaly Detection (IAD) in real-world manufacturing frequently encounters a challenging cold-start bottleneck, in which limited normal samples fail to represent the full normal distribution and only a few anomalies are available. Under such a regime, existing methods struggle …

cn, us, au, in (code pays fourni par la source)

DiTalker: A unified DiT-based framework for high-quality and style-controllable portrait animation

Feng He, Y F, Lei Fan, Donglin Di et autres

cn, au (code pays fourni par la source)

FOCA: Frequency-Oriented Cross-Domain Forgery Detection, Localization and Explanation via Multi-Modal Large Language Model

Zhou Liu, Tonghua Su, Hongshi Zhang, Fuxiang Yang et autres

Advances in image tampering techniques, particularly generative models, pose significant challenges to media verification, digital forensics, and public trust. Existing image forgery detection and localization (IFDL) methods suffer from two key limitations: over-reliance on semantic content while neglecting textural cues, and limited …

cn, au, us (code pays fourni par la source)

Learning priority-aware controllable poster layout generation

Fuxiang Yang, Wendi Hou, Lei Fan, Tonghua Su et autres

cn, au (code pays fourni par la source)

OSTE: Omni-Scene Text Editing with Latent Decoupling

Su Tonghua, Fuxiang Yang, Lei Fan, Donglin Di et autres

cn, au (code pays fourni par la source)

Noise-aware cross attention for image manipulation localization

Hongshi Zhang, Tonghua Su, Zhou Liu, Fuxiang Yang et autres

• A Gated Noise Extractor that dynamically captures noise features from multiple strategies. • Dual-granularity contrastive learning for more discriminative noise extraction. • Noise-domain guided fusion module t • reduce interference from irrelevant in- formation. • An efficient model with low parameter …

cn, au (code pays fourni par la source)

Visual Prompt-Agnostic Evolution

Junze Wang, Lei Fan, Dezheng Zhang, Weipeng Jing et autres

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often suffer from unstable training dynamics, …

Visual Prompt-Agnostic Evolution

Junze Wang, Lei Fan, Dezheng Zhang, Weipeng Jing et autres

Visual Prompt Tuning (VPT) adapts a frozen Vision Transformer (ViT) to downstream tasks by inserting a small number of learnable prompt tokens into the token sequence at each layer. However, we observe that existing VPT variants often suffer from unstable training dynamics, …

cn, au (code pays fourni par la source)