Can you provide the experiment on the SARCOS dataset?

Excuse me, where is the code for computing uniformity?

Thank you for the great work.

I am wondering if it is possible to scale up this method to transformer-based models such as ViT and GPT-2 with hundreds of millions of parameters? Are there any methods for Pareto set learning that can be applied to large models now?

I am new to the Pareto set learning field, and I would greatly appreciate your time to answer these questions.

I have some trouble evaluating the performance. Take experiments about image classification as an example,

1. Does the reported uniformity stand for the mean of uniformity computed per preference ray, but the std is not shown?
2. In Appendix A, PHN is evaluated over 25 rays, does it mean that the hyperparameters of PHN is determined w.r.t the HV over 25 points, while the HV reported in Table 1 is computed over the same 5 rays as baselines.

In the algorithm NSGA-III, the population size(the number of solutions) is larger or equal than the the number of preference rays. I use the python package pymoo to implement the algorithm NSAG-III, but I don't know which population member(the solution) corresponds to which preference rays. Thankyou for your help.