2 papers
cs.LG2026
Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems
Sean Gunn, Jorio Cocola, Oliver De Candido +2
Generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals using a single fixed complexity or dimen…
cs.CL2025
Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
Jan Betley, Jorio Cocola, Dylan Feng +4
LLMs are useful because they generalize so well. But can you have too much of a good thing? We show that a small amount of finetuning in narrow contexts can dramatically shift beha…