arXiv:2607. 24880v1 Announce Type: cross Abstract: Task-agnostic tabular embeddings are increasingly used for similarity search in real-world business systems such as Product Lifecycle Management (PLM).
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
The paper introduces TEmBed, a unified benchmark for evaluating tabular embeddings across four representation levels—cell, row, column, and table—using a diverse set of models. It demonstrates that the best model depends on the specific task and representation level, providing practical guidance for selecting embeddings in real-world applications. The study aims to facilitate the development of more general-purpose tabular representation models.
arXiv:2607. 03515v1 Announce Type: cross Abstract: In many machine learning applications, the most relevant items for a query should be efficiently retrieved.
The paper introduces PAIR, a retrieval framework that aligns with user intent preferences rather than relying on profile similarity for premium people recommendation on LinkedIn. It uses an exposure‑conditioned multi‑negative contrastive objective and incorporates click history with positional encoding to update user representations efficiently. The model, with 0.6 B parameters, achieves a MAR@100 of 0.45 on LinkedIn’s premium retrieval task.
arXiv:2607. 20737v1 Announce Type: new Abstract: Graph Neural Networks trained on heterogenous bipartite graphs form a common basis in recommendation systems.
Aligning large language models to human preferences is crucial for real-world deployment but frequently incurs an alignment tax, leading to the catastrophic forgetting of pre-trained general capabilit...
arXiv:2606. 28355v1 Announce Type: cross Abstract: Selecting which companies to approach is a central challenge in business-to-business (B2B) sales, where decisions are often based on manual research and fragmented information sources.