6 papers
Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
Vansh Gupta, Peter Nutter, Samuel Stante +5
We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, suc…
Latent Causal Diffusions for Single-Cell Perturbation Modeling
Lars Lorch, Jiaqi Zhang, Charlotte Bunne +3
Perturbation screens hold the potential to systematically map regulatory processes at single-cell resolution, yet modeling and predicting transcriptome-wide responses to perturbati…
Generative Intervention Models for Causal Perturbation Modeling
Nora Schneider, Lars Lorch, Niki Kilbertus +2
We consider the problem of predicting perturbation effects via causal models. In many applications, it is a priori unknown which mechanisms of a system are modified by an external…
Adaptable Cardiovascular Disease Risk Prediction from Heterogeneous Data using Large Language Models
Frederike Lübeck, Jonas Wildberger, Frederik Träuble +4
Cardiovascular disease (CVD) risk prediction models are essential for identifying high-risk individuals and guiding preventive actions. However, existing models struggle with the c…
Standardizing Structural Causal Models
Weronika Ormaniec, Scott Sussex, Lars Lorch +2
Synthetic datasets generated by structural causal models (SCMs) are commonly used for benchmarking causal structure learning algorithms. However, the variances and pairwise correla…
International AI Safety Report
Yoshua Bengio, Sören Mindermann, Daniel Privitera +93
The first International AI Safety Report comprehensively synthesizes the current evidence on the capabilities, risks, and safety of advanced AI systems. The report was mandated by…