This paper explores the environmental impact of the super-linear growth trends for AI from a holistic perspective, spanning Data, Algorithms, and System Hardware. We characterize...
This paper explores the environmental impact of the super-linear growth trends for AI from a holistic perspective, spanning Data, Algorithms, and System Hardware. We characterize...
In this paper, we present an algorithm to build such controllers for physically simulated characters having many degrees of freedom. Our physics-based controllers are learned by...
We propose a new form of state abstraction called goal-conditioned bisimulation that captures functional equivariance, allowing for the reuse of skills to achieve new goals.
In this work, we propose the first multi-objective BO method that is robust to input noise. We formalize our goal as optimizing the multivariate value-at-risk (MVAR), a risk...
We present experiments using real datasets with up to 15k users and items, which show that our approach obtains better trade-offs than the baselines on a variety of...
We present iSDF, a continual learning system for real-time signed distance field (SDF) reconstruction. Given a stream of posed depth images from a moving camera, it trains...
We propose Themis, a novel collective scheduling scheme that dynamically schedules collectives (divided into chunks) to balance the communication loads across all dimensions...
In this paper, we address these challenges by proposing a Spatio-Temporal Interpolation Consistency Training (STICT) framework to rationally feed the unlabeled video frames...
We take a closer look at important design choices of such methods, leading to several key improvements and resulting in a more accurate and flexible framework, which we call Sylph.
This paper presents a high-quality human motion prediction method that accurately predicts future human poses given observed ones.