Abstract: The Kappa Regression algorithm has been shown to provide great performance results, but hyper-parameter tuning can, at times, be computationally intensive. The algorithm in-cludes a single ...

Feb. 15th, 2025: The core codes have been released! More models and details will be released！ Dec. 16th, 2024: We release paper for LLaVA-Steering. Code will be released asap after internal review.

To develop the tutorial code, I referred to the repository of the MARS dataset used in the paper: [GitHub] First, as instructed in the README of the MARS repository ...

Abstract: This paper presents a novel framework for controllable graph generation through supervised fine-tuning with dynamic validation mechanisms. We propose dual prompting strategies combining rule ...