Research

Focus on the underexplored question of how to personalize these systems while preserving privacy.

Meta deploys large-scale distributed storage services across datacenters. Storage applications are often categorized based on the type and temperature of the data stored: hot, ...

Propose a framework based on diffusion models for consistent and realistic long-term novel view synthesis. Diffusion models have achieved impressive performance on many content creation applications, such as image-to-image translation and text-to- image generation.

Proposing Point Straight Flow, a model that exhibits impressive performance using one step.

we introduce an alternative formulation called “user-centric ranking” based on a transposed view, which casts ‘users’ as ‘tokens’ and ‘items’ as ‘documents’ instead. We show that this formulation has a number of advantages and shows less sign of quality saturation when trained on substantially larger data sets.

Recognizing human activities is a decades-old problem in computer vision. With recent advancements in user- assistive augmented reality and virtual reality (AR/VR) systems...

We present Galactic, a large-scale simulation and reinforcement-learning (RL) framework for robotic mobile manipulation in indoor environments.

In this paper, we present AGRoL, a novel conditional diffusion model specially purposed to track full bodies given sparse upper-body tracking signals. Our model uses a simple...

Propose to rethink visual affordances as a means to bridge vision and robotics. We argue that rich video datasets of humans interacting can offer a lot more actionable ....

We show that fine-tuning an out-of-the-box neural captioner helps to recover a plain, visually descriptive language that is more informative about image contents.