MDLM-like Models Flaw: Independent Conditionals Can't Represent Joint Distribution

kalomaze · x · 2026-08-10

kalomaze argues that MDLM-like models learn independent conditionals, not a joint distribution. For instance, 'New Carolina' isn't a real state, but parallel samples of decoupled token conditionals are blind to this. Tricks can make the independence assumption less incoherent, but the generative modeling floor remains.

Related event: Developer Highlights Theoretical Blind Spot in Discrete Diffusion Models(3 posts)→

Original post →

More from Research

Research channel →