Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Rane, Sunayana"'
Autor:
Campbell, Declan, Rane, Sunayana, Giallanza, Tyler, De Sabbata, Nicolò, Ghods, Kia, Joshi, Amogh, Ku, Alexander, Frankland, Steven M., Griffiths, Thomas L., Cohen, Jonathan D., Webb, Taylor W.
Recent work has documented striking heterogeneity in the performance of state-of-the-art vision language models (VLMs), including both multimodal language models and text-to-image models. These models are able to describe and generate a diverse array
Externí odkaz:
http://arxiv.org/abs/2411.00238
Autor:
Rane, Sunayana
As AI systems are increasingly incorporated into domains where human behavior has set the norm, a challenge for AI governance and AI alignment research is to regulate their behavior in a way that is useful and constructive for society. One way to ans
Externí odkaz:
http://arxiv.org/abs/2406.04671
Autor:
Onoe, Yasumasa, Rane, Sunayana, Berger, Zachary, Bitton, Yonatan, Cho, Jaemin, Garg, Roopal, Ku, Alexander, Parekh, Zarana, Pont-Tuset, Jordi, Tanzer, Garrett, Wang, Su, Baldridge, Jason
Vision-language datasets are vital for both text-to-image (T2I) and image-to-text (I2T) research. However, current datasets lack descriptions with fine-grained detail that would allow for richer associations to be learned by models. To fill the gap,
Externí odkaz:
http://arxiv.org/abs/2404.19753
Value alignment is essential for building AI systems that can safely and reliably interact with people. However, what a person values -- and is even capable of valuing -- depends on the concepts that they are currently using to understand and evaluat
Externí odkaz:
http://arxiv.org/abs/2310.20059
Autor:
Sucholutsky, Ilia, Muttenthaler, Lukas, Weller, Adrian, Peng, Andi, Bobu, Andreea, Kim, Been, Love, Bradley C., Grant, Erin, Groen, Iris, Achterberg, Jascha, Tenenbaum, Joshua B., Collins, Katherine M., Hermann, Katherine L., Oktar, Kerem, Greff, Klaus, Hebart, Martin N., Jacoby, Nori, Zhang, Qiuyi, Marjieh, Raja, Geirhos, Robert, Chen, Sherol, Kornblith, Simon, Rane, Sunayana, Konkle, Talia, O'Connell, Thomas P., Unterthiner, Thomas, Lampinen, Andrew K., Müller, Klaus-Robert, Toneva, Mariya, Griffiths, Thomas L.
Biological and artificial information processing systems form representations that they can use to categorize, reason, plan, navigate, and make decisions. How can we measure the extent to which the representations formed by these diverse systems agre
Externí odkaz:
http://arxiv.org/abs/2310.13018
Autor:
Rane, Sunayana, Nencheva, Mira L., Wang, Zeyu, Lew-Williams, Casey, Russakovsky, Olga, Griffiths, Thomas L.
For human children as well as machine learning systems, a key challenge in learning a word is linking the word to the visual phenomena it describes. We explore this aspect of word learning by using the performance of computer vision systems as a prox
Externí odkaz:
http://arxiv.org/abs/2207.09847
Autor:
Rane, Sunayana, Nencheva, Mira L, Wang, Zeyu, Lew-Williams, Casey, Russakovsky, Olga, Griffiths, Tom
Publikováno v:
Proceedings of the Annual Meeting of the Cognitive Science Society, vol 45, iss 45
For human children as well as machine learning systems, a key challenge in learning a word is linking the word to the visual phenomena it describes. We explore this aspect of word learning by using the performance of computer vision systems as a prox
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::85c3e63a96e6c4615d9823754e4f0ba0
https://escholarship.org/uc/item/4kb7f61t
https://escholarship.org/uc/item/4kb7f61t
Autor:
Rane, Sunayana, Nencheva, Mira L., Wang, Zeyu, Lew-Williams, Casey, Russakovsky, Olga, Griffiths, Thomas L.
For human children as well as machine learning systems, a key challenge in learning a word is linking the word to the visual phenomena it describes. By organizing model output into word categories used to analyze child language learning data, we show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2261077098f65ddcbbcff053d00c9175