arXiv:2512.11067v1 Announce Type: cross
Abstract: Traditional DBMSs execute user- or application-provided SQL queries over relational data with strong semantic guarantees and advanced query optimization, but writing complex SQL is hard and focuses only on structured tables. Contemporary multimodal systems (which operate over relations but also text, images, and even videos) either expose low-level controls that force users to use (and possibly create) machine learning UDFs manually within SQL or offload execution entirely to black-box LLMs, sacrificing usability or explainability. We propose KathDB, a new system that combines relational semantics with the reasoning power of foundation models over multimodal data. Furthermore, KathDB includes human-AI interaction channels during query parsing, execution, and result explanation, such that users can iteratively obtain explainable answers across data modalities.
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
arXiv:2512.02551v2 Announce Type: replace-cross Abstract: In this paper, we propose CUDA-L2, a system that combines large language models (LLMs) and reinforcement learning (RL) to automatically