A new research paper proposes "register tokens" as a method for bounded-state reasoning in masked diffusion language models (dLLMs), which generate text by iteratively denoising masked tokens with bidirectional attention. The work asks whether a dLLM can continue reasoning after earlier generated text is removed from context, rather than keeping that text in context to extend reasoning across generation chunks.
Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally requires keeping earlier generated text in context. We ask whether a dLLM can instead continue reasoning after that text i
EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.