Tom Freston is credited with saying ''Innovation is taking two things that exist and putting
them together in a new way''. For a long time in history, it has been the prevailing …

Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Abstract 3D-aware image synthesis encompasses a variety of tasks, such as scene
generation and novel view synthesis from images. Despite numerous task-specific methods …

We present cross-view transformers, an efficient attention-based model for map-view
semantic segmentation from multiple cameras. Our architecture implicitly learns a mapping …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

We present 3DiM, a diffusion model for 3D novel view synthesis, which is able to translate a
single input view into consistent and sharp completions across many views. The core …

Controlling electromagnetic waves and information simultaneously by information
metasurfaces is of central importance in modern society. Intelligent metasurfaces are smart …

To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

Quantifying the pathogenicity of protein variants in human disease-related genes would
have a marked effect on clinical decisions, yet the overwhelming majority (over 98%) of …

This paper develops a unified framework for image-to-image translation based on
conditional diffusion models and evaluates this framework on four challenging image-to …