Zobrazeno 1 - 10
of 32
pro vyhledávání: '"Allen, Kelsey R."'
Autor:
Wu, Ziyi, Rubanova, Yulia, Kabra, Rishabh, Hudson, Drew A., Gilitschenski, Igor, Aytar, Yusuf, van Steenkiste, Sjoerd, Allen, Kelsey R., Kipf, Thomas
We address the problem of multi-object 3D pose control in image diffusion models. Instead of conditioning on a sequence of text tokens, we propose to use a set of per-object representations, Neural Assets, to control the 3D pose of individual objects
Externí odkaz:
http://arxiv.org/abs/2406.09292
Autor:
Rubanova, Yulia, Lopez-Guevara, Tatiana, Allen, Kelsey R., Whitney, William F., Stachenfeld, Kimberly, Pfaff, Tobias
Simulating large scenes with many rigid objects is crucial for a variety of applications, such as robotics, engineering, film and video games. Rigid interactions are notoriously hard to model: small changes to the initial state or the simulation para
Externí odkaz:
http://arxiv.org/abs/2405.14045
Autor:
Lopez-Guevara, Tatiana, Rubanova, Yulia, Whitney, William F., Pfaff, Tobias, Stachenfeld, Kimberly, Allen, Kelsey R.
Accurately simulating real world object dynamics is essential for various applications such as robotics, engineering, graphics, and design. To better capture complex real dynamics such as contact and friction, learned simulators based on graph networ
Externí odkaz:
http://arxiv.org/abs/2401.11985
Autor:
Whitney, William F., Lopez-Guevara, Tatiana, Pfaff, Tobias, Rubanova, Yulia, Kipf, Thomas, Stachenfeld, Kimberly, Allen, Kelsey R.
Realistic simulation is critical for applications ranging from robotics to animation. Traditional analytic simulators sometimes struggle to capture sufficiently realistic simulation which can lead to problems including the well known "sim-to-real" ga
Externí odkaz:
http://arxiv.org/abs/2312.05359
Autor:
Allen, Kelsey R., Rubanova, Yulia, Lopez-Guevara, Tatiana, Whitney, William, Sanchez-Gonzalez, Alvaro, Battaglia, Peter, Pfaff, Tobias
Simulating rigid collisions among arbitrary shapes is notoriously difficult due to complex geometry and the strong non-linearity of the interactions. While graph neural network (GNN)-based models are effective at learning to simulate complex physical
Externí odkaz:
http://arxiv.org/abs/2212.03574
Autor:
Allen, Kelsey R., Lopez-Guevara, Tatiana, Stachenfeld, Kimberly, Sanchez-Gonzalez, Alvaro, Battaglia, Peter, Hamrick, Jessica, Pfaff, Tobias
Designing physical artifacts that serve a purpose - such as tools and other functional structures - is central to engineering as well as everyday human behavior. Though automating design has tremendous promise, general-purpose methods do not yet exis
Externí odkaz:
http://arxiv.org/abs/2202.00728
Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their capacity for flexible, creative tool use -- using objects in new ways to
Externí odkaz:
http://arxiv.org/abs/1907.09620
Humans can learn many novel tasks from a very small number (1--5) of demonstrations, in stark contrast to the data requirements of nearly tabula rasa deep learning methods. We propose an expressive class of policies, a strong but general prior, and a
Externí odkaz:
http://arxiv.org/abs/1904.06317
We propose infinite mixture prototypes to adaptively represent both simple and complex data distributions for few-shot learning. Our infinite mixture prototypes represent each class by a set of clusters, unlike existing prototypical methods that repr
Externí odkaz:
http://arxiv.org/abs/1902.04552
Autor:
Hamrick, Jessica B., Allen, Kelsey R., Bapst, Victor, Zhu, Tina, McKee, Kevin R., Tenenbaum, Joshua B., Battaglia, Peter W.
While current deep learning systems excel at tasks such as object classification, language processing, and gameplay, few can construct or modify a complex system such as a tower of blocks. We hypothesize that what these systems lack is a "relational
Externí odkaz:
http://arxiv.org/abs/1806.01203