object-permanence

Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

Revealing Occlusions with 4D Neural Fields (CVPR 2022 Oral) - Official Implementation

Tracking through Containers and Occluders in the Wild (CVPR 2023) - Official Implementation

Cognitive architecture that demonstrates how perceptual, attentional, motivational, and learning mechanisms can be progressively integrated into a robotic system to mimic aspects of infant learning

A Spiking Vision Transformer (SVT) research implementation featuring a Leaky Memory Token for energy-efficient object permanence on event-driven sensors.

Leave, come back, same world — and edit it. An explicit world ledger makes video generation return-consistent (O(1) in absence duration) and editable.