Related papers: Transforming task representations to perform novel…

Humans can continuously learn new knowledge as their experience grows. In contrast, previous learning in deep neural networks can quickly fade out when they are trained on a new task. In this paper, we hypothesize this problem can be…

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…

Biological intelligence systems of animals perceive the world by integrating information in different modalities and processing simultaneously for various tasks. In contrast, current machine learning research follows a task-specific…

We propose meta-curvature (MC), a framework to learn curvature information for better generalization and fast model adaptation. MC expands on the model-agnostic meta-learner (MAML) by learning to transform the gradients in the inner…

We present an Adversarially Pre-trained Transformer (APT) that is able to perform zero-shot meta-learning on tabular prediction tasks without pre-training on any real-world dataset, extending on the recent development of Prior-Data Fitted…

Meta-Learning has emerged as a research direction to better transfer knowledge from related tasks to unseen but related tasks. However, Meta-Learning requires many training tasks to learn representations that transfer well to unseen tasks;…

Gradient-based meta-learning techniques aim to distill useful prior knowledge from a set of training tasks such that new tasks can be learned more efficiently with gradient descent. While these methods have achieved successes in various…

Understanding the structure of multiple related tasks allows for multi-task learning to improve the generalisation ability of one or all of them. However, it usually requires training each pairwise combination of tasks together in order to…

Large language models are capable of in-context learning, the ability to perform new tasks at test time using a handful of input-output examples, without parameter updates. We develop a universal approximation theory to elucidate how…

We present a framework for learning human user models from joint-action demonstrations that enables the robot to compute a robust policy for a collaborative task with a human. The learning takes place completely automatically, without any…

We build a theoretical framework for designing and understanding practical meta-learning methods that integrates sophisticated formalizations of task-similarity with the extensive literature on online convex optimization and sequential…

Does having visual priors (e.g. the ability to detect objects) facilitate learning to perform vision-based manipulation (e.g. picking up objects)? We study this problem under the framework of transfer learning, where the model is first…

Few-shot meta-learning methods consider the problem of learning new tasks from a small, fixed number of examples, by meta-learning across static data from a set of previous tasks. However, in many real world settings, it is more natural to…

Meta-learning, or "learning to learn," is a subfield of machine learning where the goal is to develop models and algorithms that can learn from various tasks and improve their learning process over time. Unlike traditional machine learning…

Meta-learning stands for 'learning to learn' such that generalization to new tasks is achieved. Among these methods, Gradient-based meta-learning algorithms are a specific sub-class that excel at quick adaptation to new tasks with limited…

Many manipulation tasks pose a challenge since they depend on non-visual environmental information that can only be determined after sustained physical interaction has already begun. This is particularly relevant for effort-sensitive,…

Generalizing across robot embodiments and tasks is crucial for adaptive robotic systems. Modular policy learning approaches adapt to new embodiments but are limited to specific tasks, while few-shot imitation learning (IL) approaches often…

Prevailing methods for graphs require abundant label and edge information for learning. When data for a new task are scarce, meta-learning can learn from prior experiences and form much-needed inductive biases for fast adaption to new…

We present a framework for robots to learn novel visual concepts and tasks via in-situ linguistic interactions with human users. Previous approaches have either used large pre-trained visual models to infer novel objects zero-shot, or added…

In recent years, there has been a booming shift in the development of versatile, autonomous robots by introducing means to intuitively teach robots task-oriented behaviour by demonstration. In this paper, a method based on programming by…