Search Results for author: Takehiro Sato

Found 2 papers, 0 papers with code

An Implementation of Werewolf Agent That does not Truly Trust LLMs

no code implementations3 Sep 2024 Takehiro Sato, Shintaro Ozaki, Daisaku Yokoyama

Werewolf is an incomplete information game, which has several challenges when creating a computer agent as a player given the lack of understanding of the situation and individuality of utterance (e. g., computer agents are not capable of characterful utterance or situational lying).

Language Modeling Language Modelling +1

Feature-based model selection for object detection from point cloud data

no code implementations26 Sep 2022 Kairi Tokuda, Ryoichi Shinkuma, Takehiro Sato, Eiji Oki

In smart monitoring, object detection from point cloud data acquired by 3D image sensors is implemented for detecting moving objects such as vehicles and pedestrians to ensure safety on the road.

Model Selection Object +2

Cannot find the paper you are looking for? You can Submit a new open access paper.