Embodied Artificial Intelligence (Embodied AI) is crucial for achieving Artificial General
Intelligence (AGI) and serves as a foundation for various applications that bridge cyberspace …

We survey applications of pretrained foundation models in robotics. Traditional deep
learning models in robotics are trained on small datasets tailored for specific tasks, which …

We present a scene representation that brings vision and touch into a shared 3D space
which we call a tactile-augmented radiance field. This representation capitalizes on two key …

A fundamental characteristic common to both human vision and natural language is their
compositional nature. Yet despite the performance gains contributed by large vision and …

Unsupervised depth completion and estimation methods are trained by minimizing
reconstruction error. Block artifacts from resampling, intensity saturation, and occlusions are …

Abstract Three-dimensional (3D) reconstruction from a single image is an ill-posed problem
with inherent ambiguities ie scale. Predicting a 3D scene from text description (s) is similarly …

It is common to observe performance degradation when transferring models trained on
some (source) datasets to target testing data due to a domain gap between them. Existing …

Understanding neural activity and information representation is crucial for advancing
knowledge of brain function and cognition. Neural activity, measured through techniques …

Touch is an important sensing modality for humans, but it has not yet been incorporated into
a multimodal generative language model. This is partially due to the difficulty of obtaining …

The privacy-sensitive nature of decentralized datasets and the robustness of eXtreme
Gradient Boosting (XGBoost) on tabular data raise the needs to train XGBoost in the context …