Thomas Fontanari

PhD Student at the Sapienza University of Rome.
This profile is almost never used.

[Maximo Rulli @MaximoRulli]

Diffusion language models develop 𝐬𝐮𝐛𝐥𝐢𝐦𝐢𝐧𝐚𝐥⏱️

Despite receiving no explicit timestep, mask-based DLMs encode denoising progress in a low-dimensional latent structure. We can steer this clock predictably and watch the model correct perturbations across layers.

(1/6)