We propose a test for abstract causal reasoning in AI, based on scholarship in the philosophy of causation, in particular on the neuron diagrams popularized by D. Lewis. We illustrate the test on advanced Large Language Models (ChatGPT, DeepSeek and Gemini). Remarkably, these chatbots are already capable of correctly identifying causes in cases that are hotly debated in the literature. In order to assess the results of these LLMs and future dedicated AI, we propose a definition of cause in neuron diagrams with a wider validity than published hitherto, which challenges the widespread view that such a definition is elusive. We submit that these results are an illustration of how future philosophical research might evolve: as an interplay between human and artificial expertise.

EPFL scientists have developed METEOR – an application that can train algorithms to recognize new objects after being shown just a handful of images. Images taken by drones and satellites give scientists a wealth of information. These snapshots provide crucial insight into the changes taking place on the Earth's surface, such as in animal populations, vegetation, debris floating on the ocean surface and glacier coverage. In addition, experts can train neural networks to sort through the images at dizzying speed and spot and classify individual objects. "However, none of the AI programs currently available can immediately switch from recognizing one type of object to another – like from debris to a tree or building," says Professor Devis Tuia, the head of EPFL's Environmental Computational Science and Earth Observation Laboratory.

Learning from Demonstration (LfD) enables robots to acquire versatile skills by learning motion policies from human demonstrations. It endows users with an intuitive interface to transfer new skills to robots without the need for time-consuming robot programming and inefficient solution exploration. During task executions, the robot motion is usually influenced by constraints imposed by environments. In light of this, task-parameterized LfD (TP-LfD) encodes relevant contextual information into reference frames, enabling better skill generalization to new situations. However, most TP-LfD algorithms typically require multiple demonstrations across various environmental conditions to ensure sufficient statistics for a meaningful model. It is not a trivial task for robot users to create different situations and perform demonstrations under all of them. Therefore, this paper presents a novel algorithm to learn skills from few demonstrations. By leveraging the reference frame weights that capture the frame importance or relevance during task executions, our method demonstrates excellent skill acquisition performance, which is validated in real robotic environments.

Human bimanual manipulation can perform more complex tasks than a simple combination of two single arms, which is credited to the spatio-temporal coordination between the arms. However, the description of bimanual coordination is still an open topic in robotics. This makes it difficult to give an explainable coordination paradigm, let alone applied to robotics. In this work, we divide the main bimanual tasks in human daily activities into two types: leader-follower and synergistic coordination. Then we propose a relative parameterization method to learn these types of coordination from human demonstration. It represents coordination as Gaussian mixture models from bimanual demonstration to describe the change in the importance of coordination throughout the motions by probability. The learned coordinated representation can be generalized to new task parameters while ensuring spatio-temporal coordination. We demonstrate the method using synthetic motions and human demonstration data and deploy it to a humanoid robot to perform a generalized bimanual coordination motion. We believe that this easy-to-use bimanual learning from demonstration (LfD) method has the potential to be used as a data augmentation plugin for robot large manipulation model training. The corresponding codes are open-sourced in https://github.com/Skylark0924/Rofunc.

Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward functions, we investigate how the training process affects power-seeking incentives and show that they are still likely to hold for trained agents under some simplifying assumptions. We formally define the training-compatible goal set (the set of goals consistent with the training rewards) and assume that the trained agent learns a goal from this set. In a setting where the trained agent faces a choice to shut down or avoid shutdown in a new situation, we prove that the agent is likely to avoid shutdown. Thus, we show that power-seeking incentives can be probable (likely to arise for trained agents) and predictive (allowing us to predict undesirable behavior in new situations).

Natural Language Processing (NLP) has come a long way since its inception in the 1960s. In the early days, NLP focused primarily on syntactic and grammatical analysis of text. However, as technology has advanced, so too has the field of NLP. Today, NLP encompasses a wide range of techniques and applications, from sentiment analysis to machine translation to language generation. The NLP landscape of the 1960s was dominated by rule-based systems.

This paper introduces a novel method of adding intrinsic bonuses to task-oriented reward function in order to efficiently facilitate reinforcement learning search. While various bonuses have been designed to date, they are analogous to the depth-first and breadth-first search algorithms in graph theory. This paper, therefore, first designs two bonuses for each of them. Then, a heuristic gain scheduling is applied to the designed bonuses, inspired by the iterative deepening search, which is known to inherit the advantages of the two search algorithms. The proposed method is expected to allow agent to efficiently reach the best solution in deeper states by gradually exploring unknown states. In three locomotion tasks with dense rewards and three simple tasks with sparse rewards, it is shown that the two types of bonuses contribute to the performance improvement of the different tasks complementarily. In addition, by combining them with the proposed gain scheduling, all tasks can be accomplished with high performance.

Do you want to learn more about artificial intelligence? Consider adaptive AI, a revolutionary type of AI that can continuously learn and adapt to new situations and changes in its environment. Current use cases of adaptive AI are the commonly known self-driven cars and digital assistants, while the lesser-known examples are fraud detection and medical diagnosis. So, what does the future hold for adaptive AI? And what does it mean for individuals and industries?

Machines of today are already intelligent. They can process huge amounts of information hundreds of times faster than humans can do. They execute repetitive tasks without getting tired, and they easily compute very complex mathematical equations. This is why machines can detect patterns and learn from them. They outperform humans in terms of computational capabilities, but their perceptual skills are in question.

Machines of today are already intelligent. They can process huge amounts of information hundreds of times faster than humans can do. They execute repetitive tasks without getting tired, and they easily compute very complex mathematical equations. This is why machines can detect patterns and learn from them. They outperform humans in terms of computational capabilities, but their perceptual skills are in question.