"Denoising Hierarchical Representations: Joint Continuous Diffusion for Language Modeling" Continuous diffusion LMs would struggle to recover the exact tokens from noisy representations which limits text generation quality. Hierarchical Continuous Diffusion Language Models (H-CDLM) address this by jointly denoising tokens and their coarser semantic clusters, allowing higher-level information to guide token reconstruction. Applied to CoBit, it improves text generation quality by 33% on LM1B…