Deep generative models are often used for human motion prediction as they are able to
model multi-modal data distributions and characterize diverse human behavior. While much …

The ability to forecast a set of likely yet diverse possible future behaviors of an agent (eg,
future trajectories of a pedestrian) is essential for safety-critical perception systems (eg …

Measuring and promoting policy diversity is critical for solving games with strong non-
transitive dynamics where strategic cycles exist, and there is no consistent winner (eg, Rock …

Deep generative models are proven to be a useful tool for automatic design synthesis and
design space exploration. When applied in engineering design, existing generative models …

Generative data-free quantization emerges as a practical compression approach that
quantizes deep neural networks to low bit-width without accessing the real data. This …

Centralized training with decentralized execution has become an important paradigm in
multi-agent learning. Though practical, current methods rely on restrictive assumptions to …

Multi-object tracking (MOT) and trajectory prediction are two critical components in modern
3D perception systems that require accurate modeling of multi-agent interaction. We …

Deep Neural Networks (DNNs) have been extensively used in many areas including image
processing, medical diagnostics and autonomous driving. However, DNNs can exhibit …

Probabilistic forecasting consists in predicting a distribution of possible future outcomes. In
this paper, we address this problem for non-stationary time series, which is very challenging …

Abstract Knowledge distillation is an effective method for training small and efficient deep
learning models. However the efficacy of a single method can degenerate when transferring …