Are Diffusion Models Easier to Control Than Autoregressive Models?

Stefano Ermon says diffusion models are typically easier to control than autoregressive models. Generation can be steered while it is still underway, using an external reward function or a set of constraints.

An autoregressive model has to finish the whole object before anyone can tell whether it meets a constraint, stays aligned, or stays on brand. Generating a molecule when solubility matters means waiting for the full object, then scoring it with a reward function. A diffusion model generates from coarse to fine, so the check can happen progressively. From the very beginning it is possible to ask whether the object is the kind of thing wanted, then steer generation in the direction an external reward function or a set of constraints provides.

Academic literature already shows diffusion models are easier to control, and several ways of steering them exist.