Related papers: AI for the Open-World: the Learning Principles

Recent advances in artificial intelligence (AI) have achieved human-scale speed and accuracy for classification tasks. In turn, these capabilities have made AI a viable replacement for many human activities that at their core involve…

A major problem in machine learning is that of inductive bias: how to choose a learner's hypothesis space so that it is large enough to contain a solution to the problem being learnt, yet small enough to ensure reliable generalization from…

The rapid evolution of machine learning has propelled neural networks to unprecedented success across diverse domains. In particular, multimodal learning has emerged as a transformative paradigm, leveraging complementary information from…

Manufacturing lines, service journeys, supply chains, and AI reasoning chains share a common challenge: attributing a terminal outcome to the intermediate stage that caused it. We establish an information-theoretic barrier to this credit…

Most frameworks for assessing the openness of AI systems use narrow criteria such as availability of data, model, code, documentation, and licensing terms. However, to evaluate whether the intended effects of openness - such as…

The current processes for building machine learning systems require practitioners with deep knowledge of machine learning. This significantly limits the number of machine learning systems that can be created and has led to a mismatch…

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained…

World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is to enable agents to understand, predict, and interact with…

The efficiency of an AI system is contingent upon its ability to align with the specified requirements of a given task. How-ever, the inherent complexity of tasks often introduces the potential for harmful implications or adverse actions.…

As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being…

Human feedback on conversations with language language models (LLMs) is central to how these systems learn about the world, improve their capabilities, and are steered toward desirable and safe behaviors. However, this feedback is mostly…

The rise of Artificial Intelligence (AI) will bring with it an ever-increasing willingness to cede decision-making to machines. But rather than just giving machines the power to make decisions that affect us, we need ways to work…

Many challenges remain before AI agents can be deployed in real-world environments. However, one virtue of such environments is that they are inherently multi-agent and contain human experts. Using advanced social intelligence in such an…

Like any field of empirical science, AI may be approached axiomatically. We formulate requirements for a general-purpose, human-level AI system in terms of postulates. We review the methodology of deep learning, examining the explicit and…

Artificial intelligence (AI) has a history of nearly a century from its inception to the present day. We have summarized the development trends and discovered universal rules, including both success and failure. We have analyzed the reasons…

OpenAI's o3 achieves a high score of 87.5 % on ARC-AGI, a benchmark proposed to measure intelligence. This raises the question whether systems based on Large Language Models (LLMs), particularly o3, demonstrate intelligence and progress…

AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…

With the of advent rich classification models and high computational power visual recognition systems have found many operational applications. Recognition in the real world poses multiple challenges that are not apparent in controlled lab…

Nowadays service robots are leaving the structured and completely known environments and entering human-centric settings. For these robots, object perception and grasping are two challenging tasks due to the high demand for accurate and…

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…