Zobrazeno 1 - 10
of 85
pro vyhledávání: '"Sreedharan, Sarath"'
From its inception, AI has had a rather ambivalent relationship with humans -- swinging between their augmentation and replacement. Now, as AI technologies enter our everyday lives at an ever increasing pace, there is a greater need for AI systems to
Externí odkaz:
http://arxiv.org/abs/2405.15804
"Human-aware" has become a popular keyword used to describe a particular class of AI systems that are designed to work and interact with humans. While there exists a surprising level of consistency among the works that use the label human-aware, the
Externí odkaz:
http://arxiv.org/abs/2405.07773
Autor:
Sreedharan, Sarath, Mechergui, Malek
Detecting and handling misspecified objectives, such as reward functions, has been widely recognized as one of the central challenges within the domain of Artificial Intelligence (AI) safety research. However, even with the recognition of the importa
Externí odkaz:
http://arxiv.org/abs/2404.08791
One of the most difficult challenges in creating successful human-AI collaborations is aligning a robot's behavior with a human user's expectations. When this fails to occur, a robot may misinterpret their specified goals, prompting it to perform act
Externí odkaz:
http://arxiv.org/abs/2404.15184
This is the first work to look at the application of large language models (LLMs) for the purpose of model space edits in automated planning tasks. To set the stage for this union, we explore two different flavors of model space problems that have be
Externí odkaz:
http://arxiv.org/abs/2311.13720
Autor:
Chakraborti, Tathagata, Kang, Jungkoo, Muise, Christian, Sreedharan, Sarath, Walker, Michael, Szafir, Daniel, Williams, Tom
This paper describes TOBY, a visualization tool that helps a user explore the contents of an academic survey paper. The visualization consists of four components: a hierarchical view of taxonomic data in the survey, a document similarity view in the
Externí odkaz:
http://arxiv.org/abs/2306.10051
Intrigued by the claims of emergent reasoning capabilities in LLMs trained on general web corpora, in this paper, we set out to investigate their planning capabilities. We aim to evaluate (1) the effectiveness of LLMs in generating plans autonomously
Externí odkaz:
http://arxiv.org/abs/2305.15771
There is a growing interest in applying pre-trained large language models (LLMs) to planning problems. However, methods that use LLMs directly as planners are currently impractical due to several factors, including limited correctness of plans, stron
Externí odkaz:
http://arxiv.org/abs/2305.14909
In this paper, we propose a planning framework to generate a defense strategy against an attacker who is working in an environment where a defender can operate without the attacker's knowledge. The objective of the defender is to covertly guide the a
Externí odkaz:
http://arxiv.org/abs/2303.00822