2 papers
cs.AI2026
Self-Improvement for Fast, High-Quality Plan Generation
Robert Gieselmann, Henrike von Huelsen, Mihai Samson +9
Generative models trained on synthetic plan data are a promising approach to generalized planning. Recent work has focused on finding any valid plan, rather than a high-quality sol…
cs.LG2024
Towards a More Complete Theory of Function Preserving Transforms
Michael Painter
In this paper, we develop novel techniques that can be used to alter the architecture of a neural network, while maintaining the function it represents. Such operations are known a…