Search Results for author:
Found 6 papers, 3 papers with code
StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task.
Localizing Paragraph Memorization in Language Models
Can we localize the weights and mechanisms used by a language model to memorize and recite entire paragraphs of its training data?
A Roadmap to Pluralistic Alignment
We identify and formalize three possible ways to define and operationalize pluralism in AI systems: 1) Overton pluralistic models that present a spectrum of reasonable responses; 2) Steerably pluralistic models that can steer to reflect certain perspectives; and 3) Distributionally pluralistic models that are well-calibrated to a given population in distribution.
Visual Intelligence through Human Interaction
Over the last decade, Computer Vision, the branch of Artificial Intelligence aimed at understanding the visual world, has evolved from simply recognizing objects in images to describing pictures, answering questions about images, aiding robots maneuver around physical spaces and even generating novel visual content.
Approximating Human Judgment of Generated Image Quality
Generative models have made immense progress in recent years, particularly in their ability to generate high quality images.
HYPE: Human-eYe Perceptual Evaluation of Generative Models
The second, HYPE-Infinity, measures human error rate on fake and real images with no time constraints, maintaining stability and drastically reducing time and cost.
