Related papers: In-Context Policy Adaptation via Cross-Domain Skil…

Acting in human environments is a crucial capability for general-purpose robots, necessitating a robust understanding of natural language and its application to physical tasks. This paper seeks to harness the capabilities of diffusion…

Learning diverse policies for non-prehensile manipulation is essential for improving skill transfer and generalization to out-of-distribution scenarios. In this work, we enhance exploration through a two-fold approach within a hybrid…

Large-scale language models have shown the ability to adapt to a new task via conditioning on a few demonstrations (i.e., in-context learning). However, in the vision-language domain, most large-scale pre-trained vision-language (VL) models…

We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision. Map-based memory provides important contextual information for visual navigation, and…

In semi-supervised domain adaptation (SSDA), a few labeled target samples of each class help the model to transfer knowledge representation from the fully labeled source domain to the target domain. Many existing methods ignore the benefits…

We present a framework for learning to plan hierarchically in domains with unknown dynamics. We enhance planning performance by exploiting problem structure in several ways: (i) We simplify the search over plans by leveraging knowledge of…

Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. To bridge the gap between source and target domains, one prevailing strategy is…

To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture…

In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques. In this paper, we study extending ICL to address a…

In this paper, we build upon two major recent developments in the field, Diffusion Policies for visuomotor manipulation and large pre-trained multimodal foundational models to obtain a robotic skill learning system. The system can obtain…

While reinforcement learning has achieved remarkable successes in several domains, its real-world application is limited due to many methods failing to generalise to unfamiliar conditions. In this work, we consider the problem of…

Efficient and robust policy transfer remains a key challenge for reinforcement learning to become viable for real-wold robotics. Policy transfer through warm initialization, imitation, or interacting over a large set of agents with…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

Learning a generalist embodied agent capable of completing multiple tasks poses challenges, primarily stemming from the scarcity of action-labeled robotic datasets. In contrast, a vast amount of human videos exist, capturing intricate tasks…

Recent weakly supervised semantic segmentation (WSSS) methods strive to incorporate contextual knowledge to improve the completeness of class activation maps (CAM). In this work, we argue that the knowledge bias between instances and…

In meta-learning and its downstream tasks, many methods rely on implicit adaptation to task variations, where multiple factors are mixed together in a single entangled representation. This makes it difficult to interpret which factors drive…

In reinforcement learning, agents that consider the context, or current state, when selecting source policies for transfer have been shown to outperform context-free approaches. However, none of the existing approaches transfer knowledge…

The burgeoning fields of robot learning and embodied AI have triggered an increasing demand for large quantities of data. However, collecting sufficient unbiased data from the target domain remains a challenge due to costly data collection…

In real-world visual recognition problems, the assumption that the training data (source domain) and test data (target domain) are sampled from the same distribution is often violated. This is known as the domain adaptation problem. In this…