Realistic long-horizon tasks like image-goal navigation involve exploratory and exploitative
phases. Assigned with an image of the goal, an embodied agent must explore to discover …

It is fundamental for personal robots to reliably navigate to a specified goal. To study this
task, PointGoal navigation has been introduced in simulated Embodied AI environments …

Abstract Video Panoptic Segmentation (VPS) aims at assigning a class label to each pixel,
uniquely segmenting and identifying all object instances consistently across all frames …

In computer vision, models must be able to adapt to changes in image resolution to
effectively carry out tasks such as image segmentation; This is known as scale-equivariance …

We propose learnable polyphase sampling (LPS), a pair of learnable down/upsampling
layers that enable truly shift-invariant and equivariant convolutional networks. LPS can be …

While deep reinforcement learning (RL) promises freedom from hand-labeled data, great
successes, especially for Embodied AI, require significant work to create supervision via …

In the field of computer vision Vision Transformers (ViTs) have emerged as a prominent
deep learning architecture. Despite being inspired by Convolutional Neural Networks …

Modeling of real-world biological multi-agents is a fundamental problem in various scientific
and engineering fields. Reinforcement learning (RL) is a powerful framework to generate …

Cognitive science and psychology suggest that object-centric representations of complex
scenes are a promising step towards enabling efficient abstract reasoning from low-level …

Depth-aware Video Panoptic Segmentation (DVPS) is a challenging task that requires
predicting the semantic class and 3D depth of each pixel in a video, while also segmenting …