GitHub

Test-Time Optimization of Physical Query Plans with LLMs

This repository provides tools for optimizing SQL query execution plans using LLM-driven evolutionary sampling. For SQL queries, it obtains and modifies physical execution plans, benchmarks them, and ...

Google's DiffusionGemma generates 256 tokens in parallel and self-corrects as it goes

Google's open-source diffusion language model generates 256 tokens in parallel and self-corrects, hitting 4x speed on one GPU ...
IEEE

Scalable and Effective Graph Neural Networks via Trainable Random Walk Sampling

Abstract: Graph Neural Networks (GNNs) have aroused increasing research attention for their effectiveness on graph mining tasks. However, full-batch training methods based on stochastic gradient ...