arXivLLM
Hierarchical Continuous Diffusion Language Models: Coupling Discrete Tokens with Continuous Latents
層級連續擴散語言模型：結合離散 Token 與連續潛在軌跡的全新生成架構
HC-DLM couples discrete token generation with a continuous latent trajectory in a unified denoising process, overcoming key bottlenecks of prior diffusion language models in reasoning and generation tasks.
2 min read