Rollin M. Omari

activity

20202026

most citedAdversarial Robustness on Image Classification with

k

-means

1 citations · 1 across the 6 of their papers we have counts for

collaborators

Showing cs.LGShow all

2 papers · 1 filter

cs.LG2025

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment

Anh Bui, Trang Vu, Trung Le +5

In this paper, we investigate the semantic collapsing problem in generative personalization, an under-explored topic where the learned visual concept ( $V$ ) gradually shifts from it…

cs.LG2023★ 1 cited

Adversarial Robustness on Image Classification with $k$ -means

Rollin Omari, Junae Kim, Paul Montague

In this paper we explore the challenges and strategies for enhancing the robustness of $k$ -means clustering algorithms against adversarial manipulations. We evaluate the vulnerabil…

Mitigating Semantic Collapse in Generative Personalization with Test-Time Embedding Adjustment

Adversarial Robustness on Image Classification with k-means

Adversarial Robustness on Image Classification with $k$ -means