Related papers: Confidence-Building Measures for Artificial Intell…
The governance of open-weight artificial intelligence (AI) models has been framed as a binary choice: openness as risk, restriction as safety. This paper challenges that framing, arguing that access restrictions, without governed…
As artificial intelligence systems grow more capable and autonomous, frontier AI development poses potential systemic risks that could affect society at a massive scale. Current practices at many AI labs developing these systems lack…
Opinion dynamics models such as the bounded confidence models (BCMs) describe how a population can reach consensus, fragmentation, or polarization, depending on a few parameters. Connecting such models to real-world data could help…
Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside…
Enhancing model interpretability can address spurious correlations by revealing how models draw their predictions. Concept Bottleneck Models (CBMs) can provide a principled way of disclosing and guiding model behaviors through…
Research into AI alignment has grown considerably since the recent introduction of increasingly capable Large Language Models (LLMs). Unfortunately, modern methods of alignment still fail to fully prevent harmful responses when models are…
Concept Bottleneck Models (CBMs) aim for ante-hoc interpretability by learning a bottleneck layer that predicts interpretable concepts before the decision. State-of-the-art approaches typically select which concepts to learn via human…
Although AI systems are increasingly being leveraged to provide value to organizations, individuals, and society, significant attendant risks have been identified and have manifested. These risks have led to proposed regulations,…
Recent improvement gains in large language models (LLMs) have lead to everyday usage of AI-based Conversational Agents (CAs). At the same time, LLMs are vulnerable to an array of threats, including jailbreaks and, for example, causing…
Humanoid robots are drawing significant attention as versatile platforms for complex motor control, human-robot interaction, and general-purpose physical intelligence. However, achieving efficient whole-body control (WBC) in humanoids…
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…
Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…
As AI models scale to billions of parameters and operate with increasing autonomy, ensuring their safe, reliable operation demands engineering-grade security and assurance frameworks. This paper presents an enterprise-level, risk-aware,…
Embodied AI systems, including AI-powered robots that autonomously interact with the physical world, stand to be significantly advanced by Large Language Models (LLMs), which enable robots to better understand complex language commands and…
Channel knowledge maps (CKMs) provide a site-specific, location-indexed knowledge base that supports environment-aware communications and sensing in 6G networks. In practical deployments, CKM observations are often noisy and irregular due…
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…
As artificial intelligence (AI), including machine learning (ML) models and foundation models (FMs), is increasingly deployed in high-stakes domains, ensuring their trustworthiness has become a central challenge. However, the core…
Integrated Assessment Models (IAMs) are pivotal tools that synthesize knowledge from climate science, economics, and policy to evaluate the interactions between human activities and the climate system. They serve as essential instruments…
Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We…
Modeling urban crime is an important yet challenging task that requires understanding the subtle visual, social, and cultural cues embedded in urban environments. Previous work has mainly focused on rule-based agent-based modeling (ABM) and…