Ever felt like Boltzmann Generators trained with Flow Matching were doing fine, just not good enough?
We slapped Path Gradients on top — and things got better.
No extra samples, no extra compute, no changes to the model. Just gradients you already have access to.
arxiv.org/abs/2505.10139

Lorenz Vaitl, Leon Klein: Path Gradients after Flow Matching https://arxiv.org/abs/2505.10139 https://arxiv.org/pdf/2505.10139 https://arxiv.org/html/2505.10139