Comment by zimablue22

This is just GRPO (proposed by DeepSeek), which similarly samples many plausible generations, selects the best of K, and trains that sample.

Minibatch OT in flow matching also has a very similar mechanism, where samples from a noise distribution are matched to the closest data point.

There is a lot of prior work here that the authors neglect to discuss, which portrays this work as more novel than it actually is.