arXiv subjects

Wenyi Xie

Publications and source records attributed to Wenyi Xie.

3 recordsLinked to original sources

arXiv2026

ROCS: Request-Oriented Compute Sharing for Efficient Large-Scale Recommendation

Modern recommendation models gain prediction quality by scaling feature-interaction and sequence modules, but production cost constraints cap how far systems can scale. In this work, we propose Request-Oriented Compute Sharing (ROCS), a modeling and inference paradigm that exploits a unique property of recommendation inference: each user request is evaluated against many candidates, while request-side features are shared across candidates. ROCS defers request-candidate interactions as late as possible, isolates candidate-dependent representations, and evaluates substantial portions of the model once per request rather than once per candidate, significantly improving inference efficiency while maintaining or improving prediction quality. To realize this paradigm, we develop Generalized Layer Masking (GLM) to enforce candidate isolation in feature-interaction architectures, and Deep Cross Attention (DCA) to extend request-oriented sharing to sequence architectures. To support efficient GPU deployment, we co-design In-Kernel Broadcast Optimization (IKBO) that significantly accelerates ROCS model execution. Experiments on public benchmarks show that ROCS consistently improves the quality-efficiency tradeoff across recommendation backbones. On production-scale workloads, ROCS achieves up to a 3x QPS improvement on retrieval models without quality degradation and a 0.5% relative LogLoss improvement with a 50% QPS gain on a short-form video ranking model. ROCS has been deployed across large-scale recommendation systems spanning ads and organic surfaces, retrieval and ranking stages, and more than two orders of magnitude in inference complexity, delivering significant online gains at reduced infrastructure cost.

cs.LG↗

arXiv2025

An Efficient Framework for Whole-Page Reranking via Single-Modal Supervision

The whole-page reranking plays a critical role in shaping the user experience of search engines, which integrates retrieval results from multiple modalities, such as documents, images, videos, and LLM outputs. Existing methods mainly rely on large-scale human-annotated data, which is costly to obtain and time-consuming. This is because whole-page annotation is far more complex than single-modal: it requires assessing the entire result page while accounting for cross-modal relevance differences. Thus, how to improve whole-page reranking performance while reducing annotation costs is still a key challenge in optimizing search engine result pages(SERP). In this paper, we propose SMAR, a novel whole-page reranking framework that leverages strong Single-modal rankers to guide Modal-wise relevance Alignment for effective Reranking, using only limited whole-page annotation to outperform fully-annotated reranking models. Specifically, high-quality single-modal rankers are first trained on data specific to their respective modalities. Then, for each query, we select a subset of their outputs to construct candidate pages and perform human annotation at the page level. Finally, we train the whole-page reranker using these limited annotations and enforcing consistency with single-modal preferences to maintain ranking quality within each modality. Experiments on the Qilin and Baidu datasets demonstrate that SMAR reduces annotation costs by about 70-90\% while achieving significant ranking improvements compared to baselines. Further offline and online A/B testing on Baidu APPs also shows notable gains in standard ranking metrics as well as user experience indicators, fully validating the effectiveness and practical value of our approach in real-world search scenarios.

cs.IR↗

arXiv2016

Liquid Surface X-ray Studies of Gold Nanoparticle-Phospholipid Films at the Air/Water Interface

Amphiphilic phospholipids and nanoparticles functionalized with hydrophobic capping ligands have previously been extensively investigated for their capacity to self-assemble into Langmuir monolayers at the air/water interface. However, understanding of composite films consisting of both nanoparticles and phospholipids, and by extension, the complex interactions arising between nanomaterials and biological membranes, remains limited. In this work, dodecanethiol-capped gold nanoparticles (Au-NPs) with an average core diameter of 6 nm were incorporated into 1,2-dipalmitoyl-sn-glycero-3-phosphocholine (DPPC) monolayers in area ratios ranging from 0.1 to 20% area coverage at a surface pressure of 30 mN/m. High resolution liquid surface X-ray scattering studies revealed a phase separation of the DPPC and Au-NP components of the composite film, as confirmed with atomic force microscopy after the film was transferred to a substrate. At low Au-NP content, the structural organization of the phase-separated film is best described as a DPPC film containing isolated islands of Au-NPs. However, increasing the Au-NP content beyond 5% area coverage transforms the structural organization of the composite film to a long-range interconnected network of Au-NP strands surrounding small seas of DPPC, where the density of the Au-NP network increases with increasing Au-NP content. The observed phase separation and structural organization of the phospholipid and nanoparticle components in these Langmuir monolayers are useful for understanding interactions of nanoparticles with biological membranes.

cond-mat.soft↗