2 citations · 6 across the 8 of their papers we have counts for
8 papers
Story Imprinting: AI Assistants Absorb Traits from Human Characters They Resemble
Jorio Cocola, Lev McKinney, Harry Mayne +2
Language models are trained to implement a helpful AI Assistant character (e.g., Claude). We explore how finetuning on synthetic stories affects this character. Does it change the…
Tunable Latent Generative Priors for Compressed Sensing and Inverse Problems
Sean Gunn, Jorio Cocola, Oliver De Candido +2
Latent generative models have emerged as powerful priors for solving inverse problems. These models typically represent a class of natural signals at a single, fixed complexity, go…
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…
Hyper-Reduced Autoencoders for Efficient and Accurate Nonlinear Model Reductions
Jorio Cocola, John Tencer, Francesco Rizzi +2
Projection-based model order reduction on nonlinear manifolds has been recently proposed for problems with slowly decaying Kolmogorov n-width such as advection-dominated ones. Thes…
Signal Recovery with Non-Expansive Generative Network Priors
Jorio Cocola
We study compressive sensing with a deep generative network prior. Initial theoretical guarantees for efficient recovery from compressed linear measurements have been developed for…
Regularized Training of Intermediate Layers for Generative Models for Inverse Problems
Sean Gunn, Jorio Cocola, Paul Hand
Generative Adversarial Networks (GANs) have been shown to be powerful and flexible priors when solving inverse problems. One challenge of using them is overcoming representation er…
Nonasymptotic Guarantees for Spiked Matrix Recovery with Generative Priors
Jorio Cocola, Paul Hand, Vladislav Voroninski
Many problems in statistics and machine learning require the reconstruction of a rank-one signal matrix from noisy data. Enforcing additional prior information on the rank-one comp…
Global Convergence of Sobolev Training for Overparameterized Neural Networks
Jorio Cocola, Paul Hand
Sobolev loss is used when training a network to approximate the values and derivatives of a target function at a prescribed set of input points. Recent works have demonstrated its…