arXiv subjects

Ruifeng Zhao

Publications and source records attributed to Ruifeng Zhao.

3 recordsLinked to original sources

arXiv2026

WeSearch: A Unified Model-Centric Retrieval Framework for WeChat Search

We present WeSearch, a unified, model-centric retrieval framework for large-scale, continuously evolving content search. Prevailing methods assign documents fixed hierarchical Semantic IDs, implicitly assuming each document follows a single coherent semantic path-an assumption that often breaks down for multi-topic documents. WeSearch instead retrieves query-relevant clusters and then ranks atomic documents within the resulting query-specific candidate space, decoupling candidate pruning from fine-grained relevance modeling. Combined with relevance-aware training, compact document representations, and incremental index updates, this design enables weekly-or daily when needed-model refreshes. Deployed as the primary semantic retrieval path in WeChat Search alongside a lexical syntax tree, WeSearch shows consistent one-week A/B gains on corpora from hundreds of millions to billions of documents, and a one-month full-traffic A/B test confirms stable improvements of +0.68% CTR and +2.27% per-user article clicks, together with a 41% reduction in retrieval resource cost and a 19 ms reduction in graphic-text retrieval latency. WeSearch is now fully deployed in WeChat Search, serving 100% of production traffic.

cs.IR↗

arXiv2025

CPLOYO: A Pulmonary Nodule Detection Model with Multi-Scale Feature Fusion and Nonlinear Feature Learning

The integration of Internet of Things (IoT) technology in pulmonary nodule detection significantly enhances the intelligence and real-time capabilities of the detection system. Currently, lung nodule detection primarily focuses on the identification of solid nodules, but different types of lung nodules correspond to various forms of lung cancer. Multi-type detection contributes to improving the overall lung cancer detection rate and enhancing the cure rate. To achieve high sensitivity in nodule detection, targeted improvements were made to the YOLOv8 model. Firstly, the C2f\_RepViTCAMF module was introduced to augment the C2f module in the backbone, thereby enhancing detection accuracy for small lung nodules and achieving a lightweight model design. Secondly, the MSCAF module was incorporated to reconstruct the feature fusion section of the model, improving detection accuracy for lung nodules of varying scales. Furthermore, the KAN network was integrated into the model. By leveraging the KAN network's powerful nonlinear feature learning capability, detection accuracy for small lung nodules was further improved, and the model's generalization ability was enhanced. Tests conducted on the LUNA16 dataset demonstrate that the improved model outperforms the original model as well as other mainstream models such as YOLOv9 and RT-DETR across various evaluation metrics.

eess.IV↗

arXiv2014

Coronal lines and the importance of deep core-valence correlation in Ag-like ions

We report on large-scale and critically evaluated {\em ab initio} MCDHF calculations of the wavelength of the "coronal", M1 transition $4f\ ^2\mathrm{F}_{5/2}^o-^2\mathrm{F}_{7/2}^o$ in Ag-like ions. The transition between these two fine structure levels, which makes up the ground term for $Z \ge 62$ in the isoelectronic sequence, has recently been observed in Yb$^{23+}$ and W$^{27+}$, where the latter could be of great importance for fusion plasma diagnostics. We present recommended values for all members of the sequence between $Z = 50$ and $94$, which are supported by excellent agreement with values from recent experiments. The importance of including core-valence correlation with the $n=3$ shell in the theoretical model is emphasized. The results show close to spectroscopic accuracy for these forbidden lines.

physics.atom-ph↗