Summary: We propose REPresentation Alignment (REPA), a method that aligns noisy input states in diffusion models with representations from pretrained visual encoders. This significantly improves ...
Current Diffusion Language Models (DLMs) have been studied at a smaller scale compared to their autoregressive (AR) counterparts and lack fair comparison on language modeling benchmarks. Additionally, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results