BYOD: Build Your Own DLM - Efficient Autoregressive-to-Diffusion Language Model Conversion
Converts autoregressive instruction models into diffusion language models by enabling bidirectional attention and training query/value adapters on masked responses. Keeps the backbone and output head fixed, then fills several answer positions per decoding step.
First public: · Added to this list: November 2, 2026
Explore this approach
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.