Accurate 3D tracking in highly deformable scenes with occlusions and shadows can
facilitate new applications in robotics, augmented reality, and generative AI. However …

This work proposes a retrieve-and-transfer framework for zero-shot robotic manipulation,
dubbed RAM, featuring generalizability across various objects, environments, and …

This paper presents DriveTrack a new benchmark and data generation framework for long-
range keypoint tracking in real-world videos. DriveTrack is motivated by the observation that …

We propose DINOBot, a novel imitation learning framework for robot manipulation, which
leverages the image-level and pixel-level capabilities of features extracted from Vision …

We present Im2Flow2Act, a scalable learning framework that enables robots to acquire
manipulation skills from diverse data sources. The key idea behind Im2Flow2Act is to use …

To endow models with greater understanding of physics and motion, it is useful to enable
them to perceive how solid surfaces move and deform in real scenes. This can be formalized …

We address the challenge of acquiring real-world manipulation skills with a scalable
framework. Inspired by the success of large-scale auto-regressive prediction in Large …

Object tracking is central to robot perception and scene understanding, allowing robots to
parse a video stream in terms of moving objects with names. Tracking-by-detection has long …

Image-generation diffusion models have been fine-tuned to unlock new capabilities such as
image-editing and novel view synthesis. Can we similarly unlock image-generation models …

Large-scale vision foundation models have demonstrated remarkable success across
various tasks, underscoring their robust generalization capabilities. While their proficiency in …