Publications

2024

1. Boomerang: Local sampling on image manifolds using diffusion models

L. Luzi, A. Siahkoohi P. Mayer, J. Casco‐Rodriguez, and R.G. Baraniuk. 

TMLR 2024.

2. Self-Consuming Generative Models Go MAD

S. Alemohammad*, J. Casco-Rodriguez*, L. Luzi, A.I. Humayun, H. Babaei, D. LeJeune, A. Siahkoohi, and R.G. Baraniuk

ICLR 2024. Also accepted as a poster at InterfaceRice 2023.

2023

1. [Re] The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Non-Gaussian Observation Models

J. Casco-Rodriguez, C. Kemere, and R.G. Baraniuk

Under review. Also accepted as a poster at InterfaceRice 2023.

2. Provable Instance Specific Robustness via Linear Constraints

A.I. Humayun*, J. Casco-Rodriguez*, R. Balestriero, and R.G. Baraniuk

ICML 2023 Workshop on New Frontiers in Adversarial Machine Learning

3. A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices

K. Malcolm* and J. Casco-Rodriguez*.

arXiv preprint.

4. Rock Guitar Tablature Generation via Natural Language Processing

J. Casco-Rodriguez.

arXiv preprint.

Press Coverage

• AI Loses Its Mind After Being Trained on AI-Generated Data - Futurism

• When AI Is Trained on AI-Generated Data, Strange Things Start to Happen - Futurism and Yahoo! News

• AIs trained on AI-generated images produce glitches and blurs - New Scientist

• AI feeds on itself, goes MAD from its own data - Photofocus

• Scientists make AI go crazy by feeding it AI-generated content - TweakTown

• Generative AI Goes 'MAD' When Trained on AI-Created Data Over Five Times - Tom's Hardware