Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Kattakinda, Priyatham"'
Autor:
Zarei, Arman, Rezaei, Keivan, Basu, Samyadeep, Saberi, Mehrdad, Moayeri, Mazda, Kattakinda, Priyatham, Feizi, Soheil
Recent text-to-image diffusion-based generative models have the stunning ability to generate highly detailed and photo-realistic images and achieve state-of-the-art low FID scores on challenging image generation benchmarks. However, one of the primar
Externí odkaz:
http://arxiv.org/abs/2406.07844
Autor:
Kalibhat, Neha, Kattakinda, Priyatham, Zarei, Arman, Seleznev, Nikita, Sharpe, Samuel, Kumar, Senthil, Feizi, Soheil
Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from visual data
Externí odkaz:
http://arxiv.org/abs/2405.16401
Autor:
Basu, Samyadeep, Rezaei, Keivan, Kattakinda, Priyatham, Rossi, Ryan, Zhao, Cherry, Morariu, Vlad, Manjunatha, Varun, Feizi, Soheil
Identifying layers within text-to-image models which control visual attributes can facilitate efficient model editing through closed-form updates. Recent work, leveraging causal tracing show that early Stable-Diffusion variants confine knowledge prim
Externí odkaz:
http://arxiv.org/abs/2405.01008
Autor:
Moayeri, Mazda, Basu, Samyadeep, Balasubramanian, Sriram, Kattakinda, Priyatham, Chengini, Atoosa, Brauneis, Robert, Feizi, Soheil
Recent text-to-image generative models such as Stable Diffusion are extremely adept at mimicking and generating copyrighted content, raising concerns amongst artists that their unique styles may be improperly copied. Understanding how generative mode
Externí odkaz:
http://arxiv.org/abs/2404.08030
Autor:
Sadasivan, Vinu Sankar, Saha, Shoumik, Sriramanan, Gaurang, Kattakinda, Priyatham, Chegini, Atoosa, Feizi, Soheil
In this paper, we introduce a novel class of fast, beam search-based adversarial attack (BEAST) for Language Models (LMs). BEAST employs interpretable parameters, enabling attackers to balance between attack speed, success rate, and the readability o
Externí odkaz:
http://arxiv.org/abs/2402.15570
Though the background is an important signal for image classification, over reliance on it can lead to incorrect predictions when spurious correlations between foreground and background are broken at test time. Training on a dataset where these corre
Externí odkaz:
http://arxiv.org/abs/2211.10370
Autor:
Kattakinda, Priyatham, Feizi, Soheil
Standard training datasets for deep learning often contain objects in common settings (e.g., "a horse on grass" or "a ship in water") since they are usually collected by randomly scraping the web. Uncommon and rare settings (e.g., "a plane on water",
Externí odkaz:
http://arxiv.org/abs/2110.03804
Deep learning approaches in image processing predominantly resort to supervised learning. A majority of methods for image denoising are no exception to this rule and hence demand pairs of noisy and corresponding clean images. Only recently has there
Externí odkaz:
http://arxiv.org/abs/2009.11532