Results 11 to 20 of about 7,558,808 (211)
Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents [PDF]
arXiv.org, 2023 We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and multi-step ...
Zihao Wang +4 more
semanticscholar +1 more source
LayoutGPT: Compositional Visual Planning and Generation with Large Language Models [PDF]
Neural Information Processing Systems, 2023 Attaining a high degree of user controllability in visual generation often requires intricate, fine-grained inputs like layouts. However, such inputs impose a substantial burden on users when compared to simple text inputs. To address the issue, we study
Weixi Feng +8 more
semanticscholar +1 more source
Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning [PDF]
Neural Information Processing Systems, 2023 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, strong ...
L. Guan +3 more
semanticscholar +1 more source
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models [PDF]
IEEE International Conference on Computer Vision, 2022 This study focuses on using large language models (LLMs) as a planner for embodied agents that can follow natural language instructions to complete complex tasks in a visually-perceived environment.
Chan Hee Song +5 more
semanticscholar +1 more source
English and Malay language policy and planning in Malaysia [PDF]
Training, Language and Culture, 2021 The Malay-English relationship in Malaysia has witnessed a pendulum shift and ignited critical debates. The Malay nationalist discourse on language policy is evident.
Mohammad Mosiur Rahman +1 more
doaj +1 more source
SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Task Planning [PDF]
Conference on Robot Learning, 2023 Large language models (LLMs) have demonstrated impressive results in developing generalist planning agents for diverse tasks. However, grounding these plans in expansive, multi-floor, and multi-room environments presents a significant challenge for ...
Krishan Rana +5 more
semanticscholar +1 more source
Eesti ja Soome-ugri Keeleteaduse Ajakiri, 2023 This study investigates why language professionals of the standard Finnish language are unwilling to change a known problematic orthographic norm and how their arguments are based on overt and covert conceptions of standard language. It also analyzes
Henni Pajunen
doaj +1 more source
Eesti ja Soome-ugri Keeleteaduse Ajakiri, 2023 Language standardization has historically been a critical area of inquiry in language policy and planning (LPP) research. This is a political matter, which contributes to “more (and hierarchical) heterogeneity” rather than linguistic homogeneity (Gal
Kadri Koreinik
doaj +1 more source
Linguistic “Turn” of Vladimír Hurban Vladimírov [PDF]
Slovenska Literatura, 2022 Taking the work of Vladimír Hurban Vladimírov (pseudonym VHV, 1884 – 1950) as its prism, the article aims at providing an insight into the state of the language and the issue of language politics in the interwar period in the Slovak linguistic enclave in
Juliana Beňová
doaj +1 more source
Large Language Models as Commonsense Knowledge for Large-Scale Task Planning [PDF]
Neural Information Processing Systems, 2023 Large-scale task planning is a major challenge. Recent work exploits large language models (LLMs) directly as a policy and shows surprisingly interesting results. This paper shows that LLMs provide a commonsense model of the world in addition to a policy
Zirui Zhao, W. S. Lee, David Hsu
semanticscholar +1 more source