110
Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods
arXiv:2502.01384v3 Announce Type: replace-cross
Abstract: Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in Re…
Abstract: Discrete diffusion models have recently gained significant attention due to their ability to process complex discrete structures for language modeling. However, fine-tuning these models with policy gradient methods, as is commonly done in Re…