skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.


Search for: All records

Creators/Authors contains: "Kazemi, H"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. We employ an inversion-based approach to examine CLIP models. Our examination reveals that inverting CLIP models results in the generation of images that exhibit semantic alignment with the specified target prompts. We leverage these inverted images to gain insights into various aspects of CLIP models, such as their ability to blend concepts and inclusion of gender biases. We notably observe instances of NSFW (Not Safe For Work) images during model inversion. This phenomenon occurs even for semantically innocuous prompts, like "a beautiful landscape," as well as for prompts involving the names of celebrities. 
    more » « less
  2. Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact, an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully deterministic models calls into question the community's understanding of diffusion models, which relies on noise in either gradient Langevin dynamics or variational inference and paves the way for generalized diffusion models that invert arbitrary processes. 
    more » « less
  3. We demonstrate a new regime of operation to conceive radiating array oscillators. This regime is based on the dispersion engineering of coupled transmission lines (CTLs) utilizing an exceptional point of degeneracy (EPD), which represents the coalescence of multiple eigenmodes. We propose the "gain and loss balance" regime for structures exhibiting significant radiation losses to enable an innovative regime for a class of coherent EPD-based radiating oscillators with stable oscillation frequency. Moreover, this class of radiating oscillators shows an interesting trend of how the oscillation threshold scales with the length of the structure. This EPD concept has potential applications in high power-efficiency oscillators and high-power radiation. 
    more » « less
  4. We present the novel concept of exceptional points of degeneracy (EPDs), which denote a coalescence of multiple eigenmodes, that directly emerge in systems when a linear time-periodic (LTP) variation is applied. Though the presented theory is general, as an example we establish the general conditions that yield an EPD in a single LTP LC resonator with a capacitance that varies periodically in time. We show a potential application of the proposed LTP system in making sensors to exploit the ultra-sensitivity associated with operating at an EPD. 
    more » « less