Related papers: Teaching Transformers Causal Reasoning through Axi…

We present CREST, an approach for causal reasoning in simulation to learn the relevant state space for a robot manipulation policy. Our approach conducts interventions using internal models, which are simulations with approximate dynamics…

World modelling, i.e. building a representation of the rules that govern the world so as to predict its evolution, is an essential ability for any agent interacting with the physical world. Despite their impressive performance, many…

Text-based games (TBG) have emerged as promising environments for driving research in grounded language understanding and studying problems like generalization and sample efficiency. Several deep reinforcement learning (RL) methods with…

Causal representation learning promises to extend causal models to hidden causal variables from raw entangled measurements. However, most progress has focused on proving identifiability results in different settings, and we are not aware of…

Causal reasoning and compositional reasoning are two core aspirations in AI. Measuring the extent of these behaviors requires principled evaluation methods. We explore a unified perspective that considers both behaviors simultaneously,…

Explainable AI (XAI) is widely used to analyze AI systems' decision-making, such as providing counterfactual explanations for recourse. When unexpected explanations occur, users may want to understand the training data properties shaping…

Large Language Models (LLMs) have recently shown great promise in planning and reasoning applications. These tasks demand robust systems, which arguably require a causal understanding of the environment. While LLMs can acquire and reflect…

This paper investigates the logical reasoning capabilities of large language models (LLMs). For a precisely defined yet tractable formulation, we choose the conceptually simple but technically complex task of constructing proofs in Boolean…

Models need appropriate inductive biases to effectively learn from small amounts of data and generalize systematically outside of the training distribution. While Transformers are highly versatile and powerful, they can still benefit from…

Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications. This paper introduces the contextual counting task, a novel toy problem…

Recent breakthroughs in artificial intelligence have driven a paradigm shift, where large language models (LLMs) with billions or trillions of parameters are trained on vast datasets, achieving unprecedented success across a series of…

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a…

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Causal discovery amounts to unearthing causal relationships amongst features in data. It is a crucial companion to causal inference, necessary to build scientific knowledge without resorting to expensive or impossible randomised control…

The structure of causal language model training assumes that each token can be accurately predicted from the previous context. This contrasts with humans' natural writing and reasoning process, where goals are typically known before the…

In this paper, we present the Difference- Based Causality Learner (DBCL), an algorithm for learning a class of discrete-time dynamic models that represents all causation across time by means of difference equations driving change in a…

Random delays weaken the temporal correspondence between actions and subsequent state feedback, making it difficult for agents to identify the true propagation process of action effects. In cross-task scenarios, changes in task objectives…

Reconstructing accurate causal models of dynamic systems from time-series of sensor data is a key problem in many real-world scenarios. In this paper, we present an overview based on our experience about practical challenges that the causal…

Most of previous machine learning algorithms are proposed based on the i.i.d. hypothesis. However, this ideal assumption is often violated in real applications, where selection bias may arise between training and testing process. Moreover,…

One of the primary goals of Human-Robot Interaction (HRI) research is to develop robots that can interpret human behavior and adapt their responses accordingly. Adaptive learning models, such as continual and reinforcement learning, play a…