Следене
Kenneth Marino
Kenneth Marino
DeepMind
Потвърден имейл адрес: deepmind.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge
K Marino, M Rastegari, A Farhadi, R Mottaghi
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2019
6702019
The more you know: Using knowledge graphs for image classification
K Marino, R Salakhutdinov, A Gupta
CVPR 2017, 2016
4032016
The pose knows: Video forecasting by generating pose futures
J Walker, K Marino, A Gupta, M Hebert
Proceedings of the IEEE international conference on computer vision, 3332-3341, 2017
3992017
A-okvqa: A benchmark for visual question answering using world knowledge
D Schwenk, A Khandelwal, C Clark, K Marino, R Mottaghi
European Conference on Computer Vision, 146-162, 2022
1922022
Krisp: Integrating implicit and symbolic knowledge for open-domain knowledge-based vqa
K Marino, X Chen, D Parikh, A Gupta, M Rohrbach
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021
1872021
Same object, different grasps: Data and semantic knowledge for task-oriented grasping
A Murali, W Liu, K Marino, S Chernova, A Gupta
Conference on robot learning, 1540-1557, 2021
502021
Collaborating with language models for embodied reasoning
I Dasgupta, C Kaeser-Chen, K Marino, A Ahuja, S Babayan, F Hill, ...
arXiv preprint arXiv:2302.00763, 2023
392023
Ask your humans: Using human instructions to improve generalization in reinforcement learning
V Chen, A Gupta, K Marino
arXiv preprint arXiv:2011.00517, 2020
382020
Hierarchical RL Using an Ensemble of Proprioceptive Periodic Policies
K Marino, A Gupta, R Fergus, A Szlam
ICLR 2019, 2018
182018
Distilling internet-scale vision-language models into embodied agents
T Sumers, K Marino, A Ahuja, R Fergus, I Dasgupta
arXiv preprint arXiv:2301.12507, 2023
142023
Learning to navigate wikipedia by taking random walks
M Zaheer, K Marino, W Grathwohl, J Schultz, W Shang, S Babayan, ...
Advances in Neural Information Processing Systems 35, 1529-1541, 2022
42022
Real time human pose estimation for boosted random forests and pose machines
K Marino
Robotics Institute Summer Scholars (RISS) Working Papers 2, 45-49, 2014
22014
Towards Knowledge-capable AI: Agents that See, Speak, Act and Know
K Marino
Carnegie Mellon University, 2021
12021
Empirically verifying hypotheses using reinforcement learning
K Marino, R Fergus, A Szlam, A Gupta
arXiv preprint arXiv:2006.15762, 2020
12020
Controlling agents using reporter neural networks
I Dasgupta, S Chen, KD Marino, W Shang, A Ahuja
US Patent App. 18/475,157, 2024
2024
Agent as Scientist: Learning to Verify Hypotheses
K Marino, R Fergus, A Szlam, A Gupta
2019
Li Liu, Vishnu R. Desaraju, Shih-Yun Lo, and Nathan Michael
K Marino, CMM Mojica, R Illah
SUMMER SCHOLAR PROGRAM, 15, 2014
2014
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–17