Learning paths
Three source-linked diffusion language-model reading paths: foundations, inference efficiency, and controllable generation, with self-checks.
Source-linked starting points, not an exhaustive survey or a current leaderboard. Reading exercises below are suggestions, not experiments run by this site.
Foundations of diffusion language models
Read a method section and identify the state space, corruption process, training objective, and sampler.
Read inference-efficiency claims critically
Distinguish fewer network evaluations from lower wall-clock latency and identify which comparisons apply to your workload.
Choose a controllable-generation approach
Separate gradient guidance, conditional generation, and infilling before choosing a method for your constraints.