arXiv subjects

Ziwei Hong

Publications and source records attributed to Ziwei Hong.

6 recordsLinked to original sources

arXiv2026

Chain-Aware Encoding for Microservice Trace Anomaly Detection

Microservice traces can be structurally anomalous even when every span returns normally -- a payment flow that silently skips a risk check looks fine to any per-span monitor. Sequence models like DeepLog address this by predicting the next event, but they treat each API endpoint as a context-free token: the same endpoint reached through different invocation chains is mapped to the same vocabulary entry, even when its normal behavior differs across contexts. We propose encoding each event as an (endpoint, root-to-span invocation chain) pair instead. This simple change has two consequences: unseen chains are flagged without model inference, and next-event predictions become context-conditional, turning subtle path anomalies into clear outliers. We instantiate this idea in CHAINLSTM, a lightweight dual-task LSTM supporting per-event online detection. On the TrainTicket benchmark, CHAINLSTM achieves 94.3% F1 (+5.3 pp over DeepLog) with comparable latency recall and 99.1\% path recall. Case analysis shows that chain-aware encoding shifts median prediction probability on path anomalies from 0.91 to 0.002, suggesting a wider separation margin for threshold-based detection.

cs.SE↗

arXiv2026

Dynamic Interaction-Aware and Causality-Disentangled Framework for Multimodal Sentiment Analysis

Although Multimodal Sentiment Analysis (MSA) effectively leverages rich information from language, visual, and acoustic modalities, existing methods still face two core challenges: 1) static conflict suppression mechanisms fail to adapt to dynamic variations across samples, and 2) the inherent sentimental bias within the language modality, which can misguide learning from other modalities, remains entangled. To this end, we propose a Dynamic Multimodal Causal Disentanglement and Adaptive Fusion Framework (MCAF). Its cornerstone is the Multi-Granularity Causal Dynamic Router and a Conditional Diffusion Denoising Module. First, we introduce a causal intervention module based on the information bottleneck principle, which builds a Structural Causal Model to disentangle sentimental bias from language features, yielding a "de-confounded" language representation as a pure guiding signal. Second, we devise a Dynamic Multimodal Router that evaluates the interaction states (complementary, conflicting, or redundant) among visual, acoustic, and de-confounded language signals in real-time across three levels: feature, temporal, and modality, then adaptively allocates weights and routes information flow for fine-grained regulation. Finally, a lightweight Conditional Diffusion Denoising Module performs iterative denoising on the fused joint representation to explicitly filter out residual irrelevant information, generating a robust hyper-modality representation. Extensive experiments on the CMU-MOSI and CMU-MOSEI benchmarks show that MCAF sets new state-of-the-art on key classification metrics, achieving an Acc-2/F1 of 86.52%/86.51% on MOSI and 86.72%/86.65% on MOSEI, while remaining highly competitive on others. Comprehensive analyses and visualizations further validate its efficacy in dynamically perceiving interactions, disentangling bias, and enhancing interpretability.

cs.MM↗

arXiv2025

CenterMamba-SAM: Center-Prioritized Scanning and Temporal Prototypes for Brain Lesion Segmentation

Brain lesion segmentation remains challenging due to small, low-contrast lesions, anisotropic sampling, and cross-slice discontinuities. We propose CenterMamba-SAM, an end-to-end framework that freezes a pretrained backbone and trains only lightweight adapters for efficient fine-tuning. At its core is the CenterMamba encoder, which employs a novel 3x3 corner-axis-center short-sequence scanning strategy to enable center-prioritized, axis-reinforced, and diagonally compensated information aggregation. This design enhances sensitivity to weak boundaries and tiny foci while maintaining sparse yet effective feature representation. A memory-driven structural prompt generator maintains a prototype bank across neighboring slices, enabling automatic synthesis of reliable prompts without user interaction, thereby improving inter-slice coherence. The memory-augmented multi-scale decoder integrates memory attention modules at multiple levels, combining deep supervision with progressive refinement to restore fine details while preserving global consistency. Extensive experiments on public benchmarks demonstrate that CenterMamba-SAM achieves state-of-the-art performance in brain lesion segmentation.

cs.CV↗

arXiv2025

Twisted second moment of primitive cubic L-functions

We investigate the mean value of the twisted second moment of primitive cubic $L$-functions over $\mathbb{F}_q(T)$ in the non-Kummer setting. Specifically, we study the sum \begin{equation*} \sum_{\substack{\chi\ primitive\ cubic\\ genus(\chi)=g}}\chi(h_1)\bar{\chi}(h_2)|L_q(\frac{1}{2}, \chi)|^2, \end{equation*} where $L_q(s,\chi)$ denotes the $L$-function associated with primitive cubic character $\chi$. Employing a double Dirichlet series approach, we establish an error term of size

math.NT↗

arXiv2025

The first moment of central value of primitive quartic $L$-functions with fixed genus

We investigate the mean value of the first moment of primitive quartic $L$-functions over $\mathbb{F}_q(T)$ in the non-Kummer setting. Specifically, we study the sum \begin{equation*} \sum_{\substack{\chi\ primitive\ quartic\\ \chi^2 primitive\\ genus(\chi)=g}}L_q(\frac{1}{2}, \chi), \end{equation*} where $L_q(s,\chi)$ denotes the $L$-function associated with primitive quartic character $\chi$. Using double Dirichlet series, we derive an error term of size $q^{(\frac{3}{5}+\varepsilon)g}$.

math.NT↗

arXiv2025

Mean value of cubic $L$-funcitons with fixed genus

We investigate the mean value of the first moment of primitive cubic $L$-functions over $\mathbb{F}_q(T)$ in the non-Kummer setting. Specifically, we study the sum \begin{equation*} \sum_{\substack{\chi\ primitive\ cubic\\ genus(\chi)=g}}L_q(\frac{1}{2}, \chi), \end{equation*} where $L_q(s,\chi)$ denotes the $L$-function associated with primitive cubic character $\chi$. Using double Dirichlet series, we derive an error term of size $q^{(\frac{7}{8}+\varepsilon)g}$.

math.NT↗