Zobrazeno 1 - 10
of 613
pro vyhledávání: '"Alur P"'
We introduce a novel framework for human-AI collaboration in prediction and decision tasks. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to any feasible predictive algorit
Externí odkaz:
http://arxiv.org/abs/2410.08783
Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often compose fine-tun
Externí odkaz:
http://arxiv.org/abs/2410.08074
Autor:
Cen, Sarah H., Alur, Rohan
Artificial intelligence (AI) is increasingly intervening in our lives, raising widespread concern about its unintended and undeclared side effects. These developments have brought attention to the problem of AI auditing: the systematic evaluation and
Externí odkaz:
http://arxiv.org/abs/2410.04772
We study how to subvert large language models (LLMs) from following prompt-specified rules. We model rule-following as inference in propositional Horn logic, a mathematical system in which rules have the form ``if $P$ and $Q$, then $R$'' for some pro
Externí odkaz:
http://arxiv.org/abs/2407.00075
Autor:
Solko-Breslin, Alaia, Choi, Seewon, Li, Ziyang, Velingker, Neelay, Alur, Rajeev, Naik, Mayur, Wong, Eric
Many computational tasks can be naturally expressed as a composition of a DNN followed by a program written in a traditional programming language or an API call to an LLM. We call such composites "neural programs" and focus on the problem of learning
Externí odkaz:
http://arxiv.org/abs/2406.06246
We introduce a novel framework for incorporating human expertise into algorithmic predictions. Our approach leverages human judgment to distinguish inputs which are algorithmically indistinguishable, or "look the same" to predictive algorithms. We ar
Externí odkaz:
http://arxiv.org/abs/2402.00793
While automated vulnerability detection techniques have made promising progress in detecting security vulnerabilities, their scalability and applicability remain challenging. The remarkable performance of Large Language Models (LLMs), such as GPT-4 a
Externí odkaz:
http://arxiv.org/abs/2311.16169
Autor:
Pasupuleti Subrahmanya Ranjit, Zeeshan Ahmed, Swapnil Sureshchandra Bhurat, Veeresh Babu Alur, Elumalai Perumal Venkatesan, Olusegun David Samuel, Christopher Enweremadu, Algam Sai Kumar, Prabhakar Sekar
Publikováno v:
ACS Omega, Vol 9, Iss 43, Pp 43331-43352 (2024)
Externí odkaz:
https://doaj.org/article/df7fe183427d4c998a15d682d92e6579
Publikováno v:
BMC Pregnancy and Childbirth, Vol 24, Iss 1, Pp 1-12 (2024)
Abstract Background The prevalence of hypertensive disorders of pregnancy (HDPs) in India is 11%, which is one of the highest rates globally. Existing research on HDPs in India primarily focuses on biological risk factors, with minimal research on ho
Externí odkaz:
https://doaj.org/article/4944ff8b64bc4690bfbf1b8aeabd6769
Autor:
Charunayan Kamath. R, Sivakumar Alur
Publikováno v:
International Journal of Information Science and Management, Vol 22, Iss 4, Pp 225-243 (2024)
Social Media Marketing (SMM) has impacted marketing significantly in the past decade. This study uses bibliometric and content analysis to examine academic research on Social Media Marketing (SMM). Focusing on the Scopus database, the research analyz
Externí odkaz:
https://doaj.org/article/bf4ecd8bf80e4027b2c2b6a6e9747f3e