We present DINO-Tracker–a new framework for long-term dense tracking in video. The pillar
of our approach is combining test-time training on a single video, with the powerful localized …

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

Diffusion Models are popular generative modeling methods in various vision tasks, attracting
significant attention. They can be considered a unique instance of self-supervised learning …

Recent self-supervised models produce visual features that are not only effective at
encoding image-level but also pixel-level semantics. They have been reported to obtain …

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

We present the" Law of Vision Representation" in multimodal large language models
(MLLMs). It reveals a strong correlation between the combination of cross-modal alignment …

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential,
particularly in zero-shot classification across diverse distribution shifts. Building on existing …

Precise manipulation that is generalizable across scenes and objects remains a persistent
challenge in robotics. Current approaches for this task heavily depend on having a …

Internal features from large-scale pre-trained diffusion models have recently been
established as powerful semantic descriptors for a wide range of downstream tasks. Works …

In this paper, we propose ProTracker, a novel framework for robust and accurate long-term
dense tracking of arbitrary points in videos. The key idea of our method is incorporating …