The success of foundation models in language and vision motivated research in fully end-to-end robot navigation foundation models (NFMs). NFMs directly map mono...
Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However...
We propose a decoupled 3D scene generation framework called SceneMaker in this work. Due to the lack of sufficient open-set de-occlusion and pose estimation pri...
Normalizing Flows (NFs) have been established as a principled framework for generative modeling. Standard NFs consist of a forward process and a reverse process...
In this work, we explore an untapped signal in diffusion model inference. While all previous methods generate images independently at inference, we instead ask ...
The success of modern machine learning hinges on access to high-quality training data. In many real-world scenarios, such as acquiring data from public reposito...
Self-supervised pre-training has revolutionized foundation models for languages, individual 2D images and videos, but remains largely unexplored for learning 3D...
Reinforcement learning (RL), earlier proven to be effective in large language and multi-modal models, has been successfully extended to enhance 2D image generat...
All-in-One Image Restoration (AiOIR) aims to recover high-quality images from diverse degradations within a unified framework. However, existing methods often f...
Human-level contact-rich manipulation relies on the distinct roles of two key modalities: vision provides spatially rich but temporally slow global context, whi...
Recent advances in subject-driven video generation with large diffusion models have enabled personalized content synthesis conditioned on user-provided subjects...
Reasoning goes beyond language; the real world requires reasoning about space, time, affordances, and much more that words alone cannot convey. Existing multimo...
