20 citations · 40 across the 8 of their papers we have counts for
Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking
Marco Biroli
Best-of- jailbreaking (BoN) bypasses safeguards of aligned models by drawing independent augmentations of an unsafe prompt and sampling completions of each. Previous wor…
cond-mat.soft2026
Discovering and decoding latent mean-field structure with variational autoencoders
Marco Biroli, Max Welling, Vincenzo Vitelli
Generative models are increasingly used to capture correlations in many-body systems, but the representations they learn remain largely opaque to physical interpretation. Here, we…