Kyle Doherty

2 accepted papers

2025

Wayward Concepts In Multimodal Models

Brandon Trabucco, Max A Gurinas, Kyle Doherty, Russ Salakhutdinov

ICLR 2025poster

Large multimodal models such as Stable Diffusion can generate, detect, and classify new visual concepts after optimizing just the prompt. How are prompt embeddings for visual concepts found by prompt tuning methods different from typical discrete prompts? We conduct a large-scale analysis on three s…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Effective Data Augmentation With Diffusion Models

Brandon Trabucco, Kyle Doherty, Max A Gurinas, Ruslan Salakhutdinov

ICLR 2024poster

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation combines simple transformations like rotations and flips to genera…

Cited by 284 Source ↗PDF ↗code ↗Scholar ↗