Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Srinivasan Krishna"'
Autor:
Srinivasan, Krishna Prasad Varadarajan, Gumpena, Prasanth, Yattapu, Madhusudhana, Brahmbhatt, Vishal H.
In the domain of large language models (LLMs), arXiv:2305.16938 showed that few-shot full-model fine-tuning -- namely Vanilla Fine Tuning (FT) and Pattern-Based Fine Tuning (PBFT) --, and In-Context Learning (ICL) generalize similarly on Out-Of-Domai
Externí odkaz:
http://arxiv.org/abs/2405.13181
Autor:
Chukwunonso Chime, Charbel Ishak, Kishore Kumar, Muhammad Kamal, Srinivasan Krishna, Paul Kelly, Sridhar Chilimuri
Publikováno v:
Case Reports in Infectious Diseases, Vol 2019 (2019)
Immune deficiency is usually the underlying predisposing factor for cryptococcal meningitis, though there have been case reports of immunocompetent patients presenting with same. The portal of entry for Cryptococcus neoformans is the respiratory trac
Externí odkaz:
https://doaj.org/article/fee56d1263d24877a66c4a0c21991306
Web articles such as Wikipedia serve as one of the major sources of knowledge dissemination and online learning. However, their in-depth information--often in a dense text format--may not be suitable for mobile browsing, even in a responsive UI. We p
Externí odkaz:
http://arxiv.org/abs/2310.02383
Autor:
Gao, Lingyu, Chaudhary, Aditi, Srinivasan, Krishna, Hashimoto, Kazuma, Raman, Karthik, Bendersky, Michael
In-context learning (ICL) i.e. showing LLMs only a few task-specific demonstrations has led to downstream gains with no task-specific fine-tuning required. However, LLMs are sensitive to the choice of prompts, and therefore a crucial research questio
Externí odkaz:
http://arxiv.org/abs/2309.07900
Autor:
Chaudhary, Aditi, Raman, Karthik, Srinivasan, Krishna, Hashimoto, Kazuma, Bendersky, Mike, Najork, Marc
Query-document relevance prediction is a critical problem in Information Retrieval systems. This problem has increasingly been tackled using (pretrained) transformer-based models which are finetuned using large collections of labeled data. However, i
Externí odkaz:
http://arxiv.org/abs/2305.11944
Autor:
Kreiss, Elisa, Srinivasan, Krishna, Piccardi, Tiziano, Hermosillo, Jesus Adolfo, Bennett, Cynthia, Bernstein, Michael S., Morris, Meredith Ringel, Potts, Christopher
We make a first attempt to characterize image accessibility on Wikipedia across languages, present new experimental results that can inform efforts to assess description quality, and offer some strategies to improve Wikipedia's image accessibility.
Externí odkaz:
http://arxiv.org/abs/2305.09038
Autor:
Burns, Andrea, Srinivasan, Krishna, Ainslie, Joshua, Brown, Geoff, Plummer, Bryan A., Saenko, Kate, Ni, Jianmo, Guo, Mandy
Webpages have been a rich resource for language and vision-language tasks. Yet only pieces of webpages are kept: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention an
Externí odkaz:
http://arxiv.org/abs/2305.05432
Autor:
Burns, Andrea, Srinivasan, Krishna, Ainslie, Joshua, Brown, Geoff, Plummer, Bryan A., Saenko, Kate, Ni, Jianmo, Guo, Mandy
Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept in existing datasets: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resu
Externí odkaz:
http://arxiv.org/abs/2305.03668
Autor:
Yang, Jheng-Hong, Lassance, Carlos, de Rezende, Rafael Sampaio, Srinivasan, Krishna, Redi, Miriam, Clinchant, Stéphane, Lin, Jimmy
This paper presents the AToMiC (Authoring Tools for Multimedia Content) dataset, designed to advance research in image/text cross-modal retrieval. While vision-language pretrained transformers have led to significant improvements in retrieval effecti
Externí odkaz:
http://arxiv.org/abs/2304.01961
Autor:
Srinivasan, Krishna, Raman, Karthik, Samanta, Anupam, Liao, Lingrui, Bertelli, Luca, Bendersky, Mike
Large Language Models (LLMs) have shown impressive results on a variety of text understanding tasks. Search queries though pose a unique challenge, given their short-length and lack of nuance or context. Complicated feature engineering efforts do not
Externí odkaz:
http://arxiv.org/abs/2210.15718