Zobrazeno 1 - 10
of 54
pro vyhledávání: '"Gupta, Jayesh K."'
Autor:
Bodnar, Cristian, Bruinsma, Wessel P., Lucic, Ana, Stanley, Megan, Brandstetter, Johannes, Garvan, Patrick, Riechert, Maik, Weyn, Jonathan, Dong, Haiyu, Vaughan, Anna, Gupta, Jayesh K., Tambiratnam, Kit, Archibald, Alex, Heider, Elizabeth, Welling, Max, Turner, Richard E., Perdikaris, Paris
Deep learning foundation models are revolutionizing many facets of science by leveraging vast amounts of data to learn general-purpose representations that can be adapted to tackle diverse downstream tasks. Foundation models hold the promise to also
Externí odkaz:
http://arxiv.org/abs/2405.13063
Autor:
Bhattacharya, Anish, Madaan, Ratnesh, Cladera, Fernando, Vemprala, Sai, Bonatti, Rogerio, Daniilidis, Kostas, Kapoor, Ashish, Kumar, Vijay, Matni, Nikolai, Gupta, Jayesh K.
We present EvDNeRF, a pipeline for generating event data and training an event-based dynamic NeRF, for the purpose of faithfully reconstructing eventstreams on scenes with rigid and non-rigid deformations that may be too fast to capture with a standa
Externí odkaz:
http://arxiv.org/abs/2310.02437
We propose Geometric Clifford Algebra Networks (GCANs) for modeling dynamical systems. GCANs are based on symmetry group transformations using geometric (Clifford) algebras. We first review the quintessence of modern (plane-based) geometric algebra,
Externí odkaz:
http://arxiv.org/abs/2302.06594
Most state-of-the-art approaches for weather and climate modeling are based on physics-informed numerical models of the atmosphere. These approaches aim to model the non-linear dynamics and complex interactions between multiple variables, which are c
Externí odkaz:
http://arxiv.org/abs/2301.10343
Sparse and delayed rewards pose a challenge to single agent reinforcement learning. This challenge is amplified in multi-agent reinforcement learning (MARL) where credit assignment of these rewards needs to happen not only across time, but also acros
Externí odkaz:
http://arxiv.org/abs/2210.17540
Complex systems are often decomposed into modular subsystems for engineering tractability. Although various equation based white-box modeling techniques make use of such structure, learning based methods have yet to incorporate these ideas broadly. W
Externí odkaz:
http://arxiv.org/abs/2210.16294
Partial differential equations (PDEs) are central to describing complex physical system simulations. Their expensive solution techniques have led to an increased interest in deep neural network based surrogates. However, the practical utility of trai
Externí odkaz:
http://arxiv.org/abs/2209.15616
Autor:
Guillard, Benoit, Vemprala, Sai, Gupta, Jayesh K., Miksik, Ondrej, Vineet, Vibhav, Fua, Pascal, Kapoor, Ashish
Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics modeling. To alleviate this, we introduce a pipeline for data-driven simu
Externí odkaz:
http://arxiv.org/abs/2209.10986
Partial differential equations (PDEs) see widespread use in sciences and engineering to describe simulation of physical processes as scalar and vector fields interacting and coevolving over time. Due to the computationally expensive nature of their s
Externí odkaz:
http://arxiv.org/abs/2209.04934
Multi-agent reinforcement learning (MARL) provides an efficient way for simultaneously learning policies for multiple agents interacting with each other. However, in scenarios requiring complex interactions, existing algorithms can suffer from an ina
Externí odkaz:
http://arxiv.org/abs/2203.02844