arXiv:2606. 07923v1 Announce Type: cross Abstract: With the advent of Large Language Models (LLMs), many database systems introduced semantic operators that enabled analytical queries over unstructured data (e.
arXiv:2610.15235v1 Announce Type: new Abstract: Despite remarkable progress in language understanding and generation, decoder language models continue to exhibit striking failures on numerical data....
QueryFormer is a unified architecture designed for post‑click conversion rate prediction, addressing both feature interactions and sequential user behaviors. It introduces a stackable field–sequence block that generates query tokens via cross‑attention and packs sequence queries into shared‑parameter attention, improving efficiency and accuracy. The model won first place in the KDD Cup 2026 Tencent UniRec Challenge Industrial Track with an AUC of 0.83254, and scaling studies show that increasing view width slightly boosts validation AUC while maintaining low latency.
arXiv:2606. 03825v1 Announce Type: new Abstract: Transformers have become the dominant architecture for large language models, largely due to the scalability and flexibility of attention, feed-forward layers, residual connections, and normalization.
arXiv:2510. 20535v2 Announce Type: replace-cross Abstract: Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs.
arXiv:2606. 24679v1 Announce Type: cross Abstract: Data preparation pipelines improve data quality in machine learning by transforming raw tables into learning-ready data through sequential cleaning and feature transformation operators.
QUALS is a large‑scale time‑series corpus equilibrium framework designed to improve data efficiency for zero‑shot forecasting. It uses pattern quantization to decode heterogeneous patterns from mixed corpora and a learnability synchronization mechanism to calibrate sampling weights, bridging the optimization gap between simple and complex motifs. Benchmarks show that pre‑training on QUALS yields superior zero‑shot performance even with reduced training budgets.
arXiv:2606. 03040v1 Announce Type: new Abstract: Relational databases underpin modern enterprise, scientific, and healthcare systems, yet predictive machine learning on such data remains challenging due to their multi-table, heterogeneous, and temporal structure.
arXiv:2505.10202v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable success but face significant computational and memory challenges, particularly due to their e...
MetaSieve is a metapath selection layer that reduces subgraph size in relational deep learning by pruning uninformative metapaths using SQL join and aggregation statistics. It scores candidate metapath extensions with a lightweight function that favors informative yet lightweight paths, discarding those below a threshold. The method is independent of GNN parameters and, when applied to the RelBench benchmark, consistently cuts per‑epoch training time while preserving or improving accuracy.
arXiv:2610.17503v1 Announce Type: cross Abstract: Event logs are ubiquitous across real-world domains, including business processes, manufacturing workflows, healthcare, and many other operational sy...
FEAT is a foundation model designed for extremely large structured data that replaces quadratic self‑attention with a linear‑complexity dual‑axis encoding architecture. It combines an adaptive‑fusion bidirectional state‑space model with convolutional gated linear attention to achieve permutation‑invariant representation learning in O(N) time. Experiments on 12 real‑world database benchmarks show that FEAT outperforms existing structured data foundation models on zero‑shot tasks and can be up to 50× faster in inference latency.