Maximum mean discrepancy gradient flow.

Figure 1 (right), is the analog plot of Figure 1 (right), where the "random configuration" shows the statistics

We will add this in the revision.

Recently, utilizing reinforcement learning (RL) to generate molecules with desired properties has been highlighted as apromising strategy for drug design.

Text-to-image diffusion models have made significant progress in generating naturalistic images from textual inputs, and demonstrate the capacity to learn and represent complex visual-semantic relationships. While these diffusion models have achieved remarkable success, the underlying mechanisms driving their performance are not yet fully accounted for, with many unanswered questions surrounding what they learn, how they represent visual-semantic relationships, and why they sometimes fail to generalize.