相关论文: Understanding Early Word Learning in Situated Arti…

Language Models and Vision Language Models have recently demonstrated unprecedented capabilities in terms of understanding human intentions, reasoning, scene understanding, and planning-like behaviour, in text form, among many others. In…

Early in development, infants learn to extract surprisingly complex aspects of visual scenes. This early learning comes together with an initial understanding of the extracted concepts, such as their implications, causality, and using them…

We review computational and robotics models of early language learning and development. We first explain why and how these models are used to understand better how children learn language. We argue that they provide concrete theories of…

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

Recent work has shown that large text-based neural language models, trained with conventional supervised learning objectives, acquire a surprising propensity for few- and one-shot learning. Here, we show that an embodied agent situated in a…

Artificial agents, particularly humanoid robots, interact with their environment, objects, and people using cameras, actuators, and physical presence. Their communication methods are often pre-programmed, limiting their actions and…

Grounded understanding of natural language in physical scenes can greatly benefit robots that follow human instructions. In object manipulation scenarios, existing end-to-end models are proficient at understanding semantic concepts, but…

Building a dialogue system that can communicate naturally with humans is a challenging yet interesting problem of agent-based computing. The rapid growth in this area is usually hindered by the long-standing problem of data scarcity as…

Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for…

Instruction-following agents must ground language into their observation and action spaces. Learning to ground language is challenging, typically requiring domain-specific engineering or large quantities of human interaction data. To…

Learning to understand speech appears almost effortless for typically developing infants, yet from an information-processing perspective, acquiring a language from acoustic speech is an enormous challenge. This chapter reviews recent…

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied…

Children learning their first language face multiple problems of induction: how to learn the meanings of words, and how to build meaningful phrases from those words according to syntactic rules. We consider how children might solve these…

Recently, text world games have been proposed to enable artificial agents to understand and reason about real-world scenarios. These text-based games are challenging for artificial agents, as it requires an understanding of and interaction…

We present an approach for acquiring grounded representations of words from mixed-initiative, situated interactions with a human instructor. The work focuses on the acquisition of diverse types of knowledge including perceptual, semantic,…

We address the problem of bootstrapping language acquisition for an artificial system similarly to what is observed in experiments with human infants. Our method works by associating meanings to words in manipulation tasks, as a robot…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Human infants learn the names of objects and develop their own conceptual systems without explicit supervision. In this study, we propose methods for learning aligned vision-language conceptual systems inspired by infants' word learning…

Humans' experience of the world is profoundly multimodal from the beginning, so why do existing state-of-the-art language models only use text as a modality to learn and represent semantic meaning? In this paper we review the literature on…

During language acquisition, infants have the benefit of visual cues to ground spoken language. Robots similarly have access to audio and visual sensors. Recent work has shown that images and spoken captions can be mapped into a meaningful…