Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to significant differences in the output. In this work, we develop a black-box framework for generating adversarial prompts for unstructured image and text generation. These prompts, which can be standalone or prepended to benign prompts, induce specific behaviors into the generative process, such as generating images of a particular object or biasing the frequency of specific letters in the generated text. * Equal contribution.
In classical Euclidean geometry, there are several equivalent definitions of conic sections. We show that in the hyperbolic plane, the analogues of these same definitions still make sense, but are no longer equivalent, and we discuss the relationships among them.2010 Mathematics Subject Classification. Primary 51M10. Secondary 53A35, 51N15.
We introduce a statistical physics inspired supervised machine learning algorithm for classification and regression problems. The method is based on the invariances or stability of predicted results when known data are represented as expansions in terms of various stochastic functions. The algorithm predicts the classification/regression values of new data by combining (via voting) the outputs of these numerous linear expansions in randomly chosen functions. The few parameters (typically only one parameter is used in all studied examples) that this model has may be automatically optimized. The algorithm has been tested on 10 diverse training data sets of various types and feature space dimensions. It has been shown to consistently exhibit high accuracy and readily allow for optimization of parameters, while simultaneously avoiding pitfalls of existing algorithms such as those associated with class imbalance. The ensemble of stochastic functions that we use suggests a way of deriving algorithm independent bounds on the accuracy. We very briefly speculate on whether spatial coordinates in physical theories may be viewed as emergent "features" that enable a robust machine learning type description of data with generic low order smooth functions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.