Search Results for author:
Found 12 papers, 5 papers with code
Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks
Models and policies that are simultaneously differentiable and interpretable may be key enablers of this marriage.
Non-Stationary Policy Learning for Multi-Timescale Multi-Agent Reinforcement Learning
In detail, we theoretically demonstrate that the effects of non-stationarity introduced by multiple timescales can be learned by a periodic multi-agent policy.
BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting
We also show that fine-tuning pretrained models on real commercial and residential buildings improves performance for a majority of target buildings.
Plug & Play Directed Evolution of Proteins with Gradient-based Discrete MCMC
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.
Learning Canonical Embeddings for Unsupervised Shape Correspondence with Locally Linear Transformations
We present a new approach to unsupervised shape correspondence learning between pairs of point clouds.
Towards Improving the Generation Quality of Autoregressive Slot VAEs
We propose two improvements that strengthen object correlation learning.
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
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
Learning Scene Dynamics from Point Cloud Sequences
Our experimental evaluation confirms that recurrent processing of point cloud sequences results in significantly better SSFE compared to using only two frames.
Generating Scenes with Latent Object Models
We introduce a structured latent variable model that learns the underlying data-generating process for a dataset of scenes.
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize.
Learning Permutations with Sinkhorn Policy Gradient
Many problems at the intersection of combinatorics and computer science require solving for a permutation that optimally matches, ranks, or sorts some data.
Machine Learning Methods for Data Association in Multi-Object Tracking
Data association is a key step within the multi-object tracking pipeline that is notoriously challenging due to its combinatorial nature.
