The proposed layers lead toamore data efficient representation and areduction in computation by exploiting symmetry. We evaluate chirality nets on the task ofhuman poseregression, which naturally exploits theleft/right mirroring ofthe human body.

We use decision trees to convey this reasoning information, as they can be easily represented in natural language, effectively providing knowledge from prior experiments ( i.e., the impact of the generated features on performance) to

Large language models have shown tremendous performance in a variety of tasks.

Graph regression is a fundamental task that has gained significant attention in various graph learning tasks.

However, compared with the huge success of generative models in natural language processing [Tou-vron et al., 2023] and computer vision [Rombach et al., 2021], graph generation is faced with many