SAM-D2Q: Aligning Multimodal Doc2Query with Search Demand and Conversion for E-commerce
arXiv:2609.04961v2 Announce Type: replace Abstract: E-commerce search often suffers from vocabulary mismatch between user queries and merchant-authored product …
言栖资讯收录 250773 篇 AI、开发与建站文章,按发布时间排序,支持搜索与按语言筛选。
arXiv:2609.04961v2 Announce Type: replace Abstract: E-commerce search often suffers from vocabulary mismatch between user queries and merchant-authored product …
arXiv:2607.20938v2 Announce Type: replace Abstract: Traditional recommendation systems rely on latent (dense) representations, making them difficult to interpre…
arXiv:2605.18760v2 Announce Type: replace Abstract: Graph Retrieval-Augmented Generation (GraphRAG) faces significant challenges in complex relational retrieval…
arXiv:2604.22549v2 Announce Type: replace Abstract: Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manual…
arXiv:2602.08896v2 Announce Type: replace Abstract: Academic peer review remains the cornerstone of scholarly validation, yet the field faces some challenges in…
arXiv:2611.14325v1 Announce Type: cross Abstract: Text encoders turn earnings calls into vectors for search, for language models that answer from retrieved pass…
arXiv:2611.14236v1 Announce Type: cross Abstract: Transformer sentence encoders provide strong retrieval quality, but their inference cost becomes a bottleneck …
arXiv:2611.13914v1 Announce Type: cross Abstract: Recommender systems increasingly influence what users discover and consume online, yet the decision logic behi…
arXiv:2611.13595v1 Announce Type: cross Abstract: Verifying corporate financial disclosures against the International Financial Reporting Standards (IFRS) is a …
arXiv:2611.13361v1 Announce Type: cross Abstract: Modern e-commerce platforms naturally provide three complementary modalities: textual item descriptions, item …
arXiv:2611.13127v1 Announce Type: cross Abstract: Retrieval-augmented language model systems generally select context by query-conditioned relevance. We argue t…
arXiv:2611.13069v1 Announce Type: cross Abstract: Banks now train foundation models on ordered sequences of customer events such as transactions, app sessions, …
arXiv:2611.12918v1 Announce Type: cross Abstract: Offline web-behavior benchmarks frequently insert the demonstrated action into a finite candidate set and then…
arXiv:2611.14477v1 Announce Type: new Abstract: Text-to-SQL systems over large pooled catalogs must first retrieve the tables a question needs. We compare again…
arXiv:2611.14220v1 Announce Type: new Abstract: Next point-of-interest (POI) prediction supports personalized location services by anticipating users' next dest…
arXiv:2611.14149v1 Announce Type: new Abstract: Information seeking in large language model (LLM) systems increasingly involves decisions about when to acquire …
arXiv:2611.14050v1 Announce Type: new Abstract: Retrieving evidence from Indian Knowledge Systems is complicated by transliteration variants, ambiguous names, a…
arXiv:2611.14037v1 Announce Type: new Abstract: Many heritage institutions hold extensive collections of show programs. Too numerous to be cataloged individuall…
arXiv:2611.14004v1 Announce Type: new Abstract: As multimodal tourism-related information collected from heterogeneous data sources has become increasingly avai…
arXiv:2611.13972v1 Announce Type: new Abstract: Modern recommender systems increasingly consider diverse data modalities to enhance model performance. However, …