Africa
Model-Based Imitation Learning for Urban Driving
MILE is action-conditioned, allowing us to model how other agents respond to ego-actions. We show that our model can predict plausible and diverse futures from latent states and actions over long time horizons.
Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting
Multivariate time-series forecasting plays a crucial role in many real-world applications.
Biologically plausible solutions for spiking networks with efficient coding
To inform the understanding of the function and dynamics of biological networks in the brain, however, the mathematical models have to be informed by biology and obey the same constraints as biological networks.
Scheduling jobs with stochastic holding costs
This question is motivated by several applications.
CO-Optimal Transport
COOT leads to performance improvements over the state-of-the-art methods.
Support Recovery of Sparse Signals from a Mixture of Linear Measurements
Both of these problems have also received attention recently.
Neural Program Generation Modulo Static Analysis
The root cause of these issues, we believe, is that current neural models of code treat programs as text rather than artifacts that are constructed following a semantics . In principle, a model could learn semantics from syntax given enough data.