Zobrazeno 1 - 10
of 42
pro vyhledávání: '"Carl Vondrick"'
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
Abstract Behavior modeling is an essential cognitive ability that underlies many aspects of human and animal social behavior (Watson in Psychol Rev 20:158, 1913), and an ability we would like to endow robots. Most studies of machine behavior modellin
Externí odkaz:
https://doaj.org/article/cd7a91c276d741a38635cc2a85203743
Publikováno v:
Science robotics. 7(68)
Internal computational models of physical bodies are fundamental to the ability of robots and animals alike to plan and control their actions. These “self-models” allow robots to consider outcomes of multiple possible future actions without tryin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ffbd68c1d94e2405529d853ac18cbdb5
https://pubmed.ncbi.nlm.nih.gov/35857575
https://pubmed.ncbi.nlm.nih.gov/35857575
Autor:
Terrance Boult, Przemyslaw Grabowicz, Derek Prijatelj, Roni Stern, Lawrence Holder, Joshua Alspector, Mohsen M. Jafarzadeh, Toqueer Ahmad, Akshay Dhamija, Chunchun Li, Steve Cruz, Abhinav Shrivastava, Carl Vondrick, Scheirer Walter
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:15047-15052
Managing inputs that are novel, unknown, or out-of-distribution is critical as an agent moves from the lab to the open world. Novelty-related problems include being tolerant to novel perturbations of the normal input, detecting when the input include
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9a81cc59c1fbb827fc6cc5bfdc9912b3
https://doi.org/10.1609/aaai.v35i17.17766
https://doi.org/10.1609/aaai.v35i17.17766
Autor:
Pierre Gentine, Galen McKinley, Tian Zheng, Courtney Cogburn, Ryan Abernathey, Laure Zanna, Carl Vondrick, Vanessa Burbano, Andrew Revkin, David Lawrence, Michael Pritchard
LEAP's Strategic Plan articulates the Center'svision, mission, values, and goals. LEAP’s Strategic Plan will serve as a guide for setting priorities, allocating resources, assessing capabilities, and identifying needs to define the new discipline o
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5e79879015ee07c88e9aa360974994c9
Publikováno v:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68b26759c9596b16dbdc0bdd07aa329d
https://doi.org/10.18653/v1/2022.acl-long.81
https://doi.org/10.18653/v1/2022.acl-long.81
Autor:
Yinzhi Cao, Yuchi Tian, Suman Jana, Shiqi Wang, Justin Whitehouse, Junfeng Yang, Carl Vondrick, Baishakhi Ray, Kexin Pei
Publikováno v:
ACM SIGOPS Operating Systems Review. 53:59-67
Deep learning (DL) systems are increasingly deployed in safety- and security-critical domains including autonomous driving, robotics, and malware detection, where the correctness and predictability of a system on corner-case inputs are of great impor
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b05b1b43d2978d58afbebaeb71718a19
https://doi.org/10.1145/3352020.3352030
https://doi.org/10.1145/3352020.3352030
Publikováno v:
Scientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
Scientific Reports
Scientific Reports
Behavior modeling is an essential cognitive ability that underlies many aspects of human and animal social behavior (Watson in Psychol Rev 20:158, 1913), and an ability we would like to endow robots. Most studies of machine behavior modelling, howeve
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6e864ae158b3a93004477611ce23b535
https://doi.org/10.1038/s41598-020-77918-x
https://doi.org/10.1038/s41598-020-77918-x
Publikováno v:
CVPR
We introduce a framework for learning from unlabeled video what is predictable in the future. Instead of committing up front to features to predict, our approach learns from data which features are predictable. Based on the observation that hyperboli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9a93cbf3ee07f38160cba86d453312c0
http://arxiv.org/abs/2101.01600
http://arxiv.org/abs/2101.01600
Autor:
Ying Lin, Jiawei Han, Yi Fung, Manling Li, Shih-Fu Chang, Qing Lyu, Ben Zhou, Xudong Lin, Haoyu Wang, Chris Callison-Burch, Martha Palmer, Alexander Dong, Xiaodong Yu, Piyush Mishra, Dídac Surís, Tuan Lai, Hongming Zhang, Zhenhailong Wang, Susan Brown, Dan Roth, Brian Chen, Carl Vondrick, Sha Li, Haoyang Wen, Heng Ji, Xiaoman Pan
Publikováno v:
NAACL-HLT (Demonstrations)
We present a new information extraction system that can automatically construct temporal event graphs from a collection of news documents from multiple sources, multiple languages (English and Spanish for our experiment), and multiple data modalities
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0a91a564d13c60de74c9e20fa3758dba
https://doi.org/10.18653/v1/2021.naacl-demos.16
https://doi.org/10.18653/v1/2021.naacl-demos.16
Publikováno v:
CVPR
We introduce a framework for learning robust visual representations that generalize to new viewpoints, backgrounds, and scene contexts. Discriminative models often learn naturally occurring spurious correlations, which cause them to fail on images ou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d5ad428654f6275d3e21a2f2d5c27732
http://arxiv.org/abs/2012.12265
http://arxiv.org/abs/2012.12265