Related papers: VertiCoder: Self-Supervised Kinodynamic Representa…

Control policy learning for modular robot locomotion has previously been limited to proprioceptive feedback and flat terrain. This paper develops policies for modular systems with vision traversing more challenging environments. These…

Most self-supervised video representation learning approaches focus on action recognition. In contrast, in this paper we focus on self-supervised video learning for movie understanding and propose a novel hierarchical self-supervised…

Event-based cameras are dynamic vision sensors that provide asynchronous measurements of changes in per-pixel brightness at a microsecond level. This makes them significantly faster than conventional frame-based cameras, and an appealing…

Visual robotic manipulation research and applications often use multiple cameras, or views, to better perceive the world. How else can we utilize the richness of multi-view data? In this paper, we investigate how to learn good…

The rapidly evolving field of robotics necessitates methods that can facilitate the fusion of multiple modalities. Specifically, when it comes to interacting with tangible objects, effectively combining visual and tactile sensory data is…

Learning effective visuomotor policies for robots purely from data is challenging, but also appealing since a learning-based system should not require manual tuning or calibration. In the case of a robot operating in a real environment the…

This paper tackles a significant challenge faced by Vision Transformers (ViTs): their constrained scalability across different image resolutions. Typically, ViTs experience a performance decline when processing resolutions different from…

This paper investigates two techniques for developing efficient self-supervised vision transformers (EsViT) for visual representation learning. First, we show through a comprehensive empirical study that multi-stage architectures with…

Simulation offers a scalable and efficient alternative to real-world data collection for learning visuomotor robotic policies. However, the simulation-to-reality, or Sim2Real distribution shift -- introduced by employing simulation-trained…

Vision-Language-Action (VLA) models have emerged as a promising framework for end-to-end autonomous driving. However, existing VLAs typically rely on sparse action supervision, which underutilizes their powerful scene understanding and…

The choice of visual representation is key to scaling generalist robot policies. However, direct evaluation via policy rollouts is expensive, even in simulation. Existing proxy metrics focus on the representation's capacity to capture…

In this work we explore a new approach for robots to teach themselves about the world simply by observing it. In particular we investigate the effectiveness of learning task-agnostic representations for continuous control tasks. We extend…

In this paper, we investigate how to achieve better visual grounding with modern vision-language transformers, and propose a simple yet powerful Selective Retraining (SiRi) mechanism for this challenging task. Particularly, SiRi conveys a…

Existing RGB-based imitation learning approaches typically employ traditional vision encoders such as ResNet or ViT, which lack explicit 3D reasoning capabilities. Recent geometry-grounded vision models, such as VGGT~\cite{wang2025vggt},…

We present a visual imitation learning framework that enables learning of robot action policies solely based on expert samples without any robot trials. Robot exploration and on-policy trials in a real-world environment could often be…

Learning-based methods are promising to plan robot motion without performing extensive search, which is needed by many non-learning approaches. Recently, Value Iteration Networks (VINs) received much interest since---in contrast to standard…

We introduce an unsupervised feature learning approach that embeds 3D shape information into a single-view image representation. The main idea is a self-supervised training objective that, given only a single 2D image, requires all unseen…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Videos captured from multiple viewpoints can help in perceiving the 3D structure of the world and benefit computer vision tasks such as action recognition, tracking, etc. In this paper, we present a method for self-supervised learning from…

It is challenging for humans -- particularly those living with physical disabilities -- to control high-dimensional, dexterous robots. Prior work explores learning embedding functions that map a human's low-dimensional inputs (e.g., via a…