Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Zuo, Max"'
Many recent works have explored using language models for planning problems. One line of research focuses on translating natural language descriptions of planning tasks into structured planning languages, such as the planning domain definition langua
Externí odkaz:
http://arxiv.org/abs/2407.03321
Object rearrangement is the problem of enabling a robot to identify the correct object placement in a complex environment. Prior work on object rearrangement has explored a diverse set of techniques for following user instructions to achieve some des
Externí odkaz:
http://arxiv.org/abs/2310.00371
Autor:
Mirzazadeh, Ali, Dubost, Florian, Pike, Maxwell, Maniar, Krish, Zuo, Max, Lee-Messer, Christopher, Rubin, Daniel
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input, with sometime
Externí odkaz:
http://arxiv.org/abs/2210.09705
Modern day computer games have extremely large state and action spaces. To detect bugs in these games' models, human testers play the games repeatedly to explore the game and find errors in the games. Such gameplay is exhaustive and time consuming. M
Externí odkaz:
http://arxiv.org/abs/2203.12774
Publikováno v:
Proceedings of the Annual Meeting of the Cognitive Science Society, vol 45, iss 45
Prototype and exemplar models have each found support in the cognitive science literature on human concepts and categorization. The two model classes have complementary strengths. Prototype models can be more computationally efficient and interpretab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od_______325::f9600c2c07e30e2391e722b7acd4003e
https://escholarship.org/uc/item/0tz7w767
https://escholarship.org/uc/item/0tz7w767
Autor:
Mirzazadeh, Ali, Dubost, Florian, Pike, Maxwell, Maniar, Krish, Zuo, Max, Lee-Messer, Christopher, Rubin, Daniel
Publikováno v:
2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV).
Attention--or attribution--maps methods are methods designed to highlight regions of the model's input that were discriminative for its predictions. However, different attention maps methods can highlight different regions of the input, with sometime
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ddd96cb9082572fea9e27af1d0267714
https://doi.org/10.1109/wacv56688.2023.00192
https://doi.org/10.1109/wacv56688.2023.00192
