Gilad
@giladturok
1/ 🚨 New paper! DUEL: Exact Likelihood for Masked Diffusion via Deterministic Unmasking
We give masked diffusion models (MDMs) proper likelihood — and therefore proper perplexity — for the first time. Turns out MDMs are closer to autoregressive models than previously thought.
We give masked diffusion models (MDMs) proper likelihood — and therefore proper perplexity — for the first time. Turns out MDMs are closer to autoregressive models than previously thought.
2 149