Related papers: HALMA: Humanlike Abstraction Learning Meets Afford…

Conceptual abstraction and analogy-making are key abilities underlying humans' abilities to learn, reason, and robustly adapt their knowledge to new domains. Despite of a long history of research on constructing AI systems with these…

LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world settings. We propose a case-based learning framework that…

Developing algorithms that are able to generalize to a novel task given only a few labeled examples represents a fundamental challenge in closing the gap between machine- and human-level performance. The core of human cognition lies in the…

Achieving human-like spatial intelligence for vision-language models (VLMs) requires inferring 3D structures from 2D observations, recognizing object properties and relations in 3D space, and performing high-level spatial reasoning. In this…

In many real-world scenarios, an autonomous agent often encounters various tasks within a single complex environment. We propose to build a graph abstraction over the environment structure to accelerate the learning of these tasks. Here,…

Recent advances in visual reasoning (VR), particularly with the aid of Large Vision-Language Models (VLMs), show promise but require access to large-scale datasets and face challenges such as high computational costs and limited…

In natural languages, words are used in association to construct sentences. It is not words in isolation, but the appropriate combination of hierarchical structures that conveys the meaning of the whole sentence. Neural networks can capture…

This paper presents a framework for learning state and action abstractions in sequential decision-making domains. Our framework, planning abstraction from language (PARL), utilizes language-annotated demonstrations to automatically discover…

According to a mainstream position in contemporary cognitive science and philosophy, the use of abstract compositional concepts is both a necessary and a sufficient condition for the presence of genuine thought. In this article, we show how…

Structural causal models provide a formalism to express causal relations between variables of interest. Models and variables can represent a system at different levels of abstraction, whereby relations may be coarsened and refined according…

The unprecedented performance of large language models (LLMs) necessitates improvements in evaluations. Rather than merely exploring the breadth of LLM abilities, we believe meticulous and thoughtful designs are essential to thorough,…

The abilities of humans to understand the world in terms of cause and effect relationships, as well as to compress information into abstract concepts, are two hallmark features of human intelligence. These two topics have been studied in…

We propose a method to systematically represent both the static and the dynamic components of environments, i.e. objects and agents, as well as the changes that are happening in the environment, i.e. the actions and skills performed by…

The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has…

Collective learning can be greatly enhanced when agents effectively exchange knowledge with their peers. In particular, recent work studying agents that learn to teach other teammates has demonstrated that action advising accelerates…

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to improve it remains unexplored. In this work, we design the…

Strong inductive biases give humans the ability to quickly learn to perform a variety of tasks. Although meta-learning is a method to endow neural networks with useful inductive biases, agents trained by meta-learning may sometimes acquire…

This paper presents an in-depth analysis of Large Language Models (LLMs), focusing on LLaMA, a prominent open-source foundational model in natural language processing. Instead of assessing LLaMA through its generative output, we design…

Human activity understanding is of widespread interest in artificial intelligence and spans diverse applications like health care and behavior analysis. Although there have been advances in deep learning, it remains challenging. The object…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…