Language models (LMs) have demonstrated their capability in possessing commonsense knowledge of the physical world, a crucial aspect performing tasks everyday life. However, it remains unclear whether they capacity to generate grounded, executable plans for embodied tasks. This is challenging task as LMs lack ability perceive environment through vision and feedback from environment. In this pap...

Patients with classic galactosemia, an inborn error of metabolism, have speech and language production impairments. Past research primarily focused on speech (motor) problems, but these cannot solely explain the language impairments. Which specific deficits contribute to the impairments in language production is not yet known. Deficits in semantic and syntactic planning are plausible and requir...

PURPOSE To determine the accuracy of functional MR imaging in locating language areas for planning surgical resection. METHODS Intraoperative photographs were digitized and overlaid on functional MR language maps. The sensitivity and specificity of functional MR imaging for identifying language areas were determined for five different language tasks by comparing functional MR areas of languag...

AI planning requires action models to be given in advance. However, it is both time consuming and tedious for a human to encode the action models by hand using a formal language such as PDDL, as a result, learning action models is important for AI planning. On the other hand, the data being used to learn action models are often limited in planning domains, which makes the learning task very dif...

We discuss an application of planning to data processing, a planning problem which poses unique challenges for domain description languages. We discuss these challenges and why the current PDDL standard does not meet them. We discuss DPADL (Data Processing Action Description Language), a language for describing planning domains that involve data processing. DPADL is a declarative, object-orient...

The fields of language production and verbal memory have relatively little contact. I argue that utterance planning for language production has substantial memory maintenance demands and that utterance planning provides the maintenance and ordering processes for short-term verbal memory tasks. There has already been some movement toward this view. I discuss benefits to pursuing these links more...

While classical planning is still mostly concerned with sequential plans, numerous realistic domains are inherently concurrent. Especially planning for multi-agent systems necessitates a clear formal concept of plans in such domains. This paper presents a basic semantic model for concurrent plans using actions with arbitrary effects over time and shared accesses to resources. Two complementary ...