no code implementations • 7 Feb 2024 • Peter Graf, Patrick Emami
Models and policies that are simultaneously differentiable and interpretable may be key enablers of this marriage.
no code implementations • 17 Jul 2023 • Patrick Emami, Xiangyu Zhang, David Biagioni, Ahmed S. Zamzam
In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy.
1 code implementation • NeurIPS 2023 • Patrick Emami, Abhijeet Sahu, Peter Graf
We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings.
1 code implementation • 20 Dec 2022 • Patrick Emami, Aidan Perreault, Jeffrey Law, David Biagioni, Peter C. St. John
We introduce a sampling framework for evolving proteins in silico that supports mixing and matching a variety of unsupervised models, such as protein language models, and supervised models that predict protein function from sequence.
no code implementations • 5 Sep 2022 • Pan He, Patrick Emami, Sanjay Ranka, Anand Rangarajan
We present a new approach to unsupervised shape correspondence learning between pairs of point clouds.
1 code implementation • 3 Jun 2022 • Patrick Emami, Pan He, Sanjay Ranka, Anand Rangarajan
We propose two improvements that strengthen object correlation learning.
no code implementations • 23 Mar 2022 • Pan He, Patrick Emami, Sanjay Ranka, Anand Rangarajan
Scene flow estimation is therefore converted into the problem of recovering motion from the alignment of probability density functions, which we achieve using a closed-form expression of the classic Cauchy-Schwarz divergence.
Self-Supervised Learning Self-supervised Scene Flow Estimation
no code implementations • 16 Nov 2021 • Pan He, Patrick Emami, Sanjay Ranka, Anand Rangarajan
Our experimental evaluation confirms that recurrent processing of point cloud sequences results in significantly better SSFE compared to using only two frames.
no code implementations • 29 Sep 2021 • Patrick Emami, Pan He, Sanjay Ranka, Anand Rangarajan
We introduce a structured latent variable model that learns the underlying data-generating process for a dataset of scenes.
1 code implementation • 7 Jun 2021 • Patrick Emami, Pan He, Sanjay Ranka, Anand Rangarajan
Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize.
1 code implementation • 18 May 2018 • Patrick Emami, Sanjay Ranka
Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data.
no code implementations • 19 Feb 2018 • Patrick Emami, Panos M. Pardalos, Lily Elefteriadou, Sanjay Ranka
Data association is a key step within the multi-object tracking pipeline that is notoriously challenging due to its combinatorial nature.