English
Related papers

Related papers: Modeling AGI Safety Frameworks with Causal Influen…

200 papers

We present a comprehensive study of graphical log-linear models for contingency tables. High dimensional contingency tables arise in many areas such as computational biology, collection of survey and census data and others. Analysis of…

Methodology · Statistics 2016-03-15 Niharika Gauraha

For autonomous vehicles, safe navigation in complex environments depends on handling a broad range of diverse and rare driving scenarios. Simulation- and scenario-based testing have emerged as key approaches to development and validation of…

Causal modelling is a tool for generating causal explanations of observed correlations and has led to a deeper understanding of correlations in quantum networks. Existing frameworks for quantum causality tend to focus on acyclic causal…

Quantum Physics · Physics 2024-03-14 V. Vilasini , Roger Colbeck

Algorithmic decisions about individuals require predictions that are not only accurate but also fair with respect to sensitive attributes such as gender and race. Causal notions of fairness align with legal requirements, yet many methods…

Machine Learning · Statistics 2026-03-02 Yoichi Chikahara

Training vision models to detect workplace hazards accurately requires realistic images of unsafe conditions that could lead to accidents. However, acquiring such datasets is difficult because capturing accident-triggering scenarios as they…

Artificial Intelligence · Computer Science 2025-11-19 Sanjay Acharjee , Abir Khan Ratul , Diego Patino , Md Nazmus Sakib

Imitation learning is a powerful approach for learning autonomous driving policy by leveraging data from expert driver demonstrations. However, driving policies trained via imitation learning that neglect the causal structure of expert…

Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…

Computers and Society · Computer Science 2024-11-14 Arthur Goemans , Marie Davidsen Buhl , Jonas Schuett , Tomek Korbak , Jessica Wang , Benjamin Hilton , Geoffrey Irving

Ensuring that AI systems reliably and robustly avoid harmful or dangerous behaviours is a crucial challenge, especially for AI systems with a high degree of autonomy and general intelligence, or systems used in safety-critical contexts. In…

This work in progress considers reachability-based safety analysis in the domain of autonomous driving in multi-agent systems. We formulate the safety problem for a car following scenario as a differential game and study how different…

Systems and Control · Electrical Eng. & Systems 2021-12-30 Gilbert Bahati , Marsalis Gibson , Alexandre Bayen

Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough to significantly harm humanity. We identify four areas of…

In the field of conditional autonomous driving technology, driver perceived risk prediction plays a crucial role in reducing traffic risks and ensuring passenger safety. This study introduces an innovative perceived risk prediction model…

Human-Computer Interaction · Computer Science 2025-03-07 Chenhao Yang , Siwei Huang , Chuan Hu

Uncertainties in the real world mean that is impossible for system designers to anticipate and explicitly design for all scenarios that a robot might encounter. Thus, robots designed like this are fragile and fail outside of…

Robotics · Computer Science 2023-10-02 Ricardo Cannizzaro , Jonathan Routley , Lars Kunze

As foundation models grow in both popularity and capability, researchers have uncovered a variety of ways that the models can pose a risk to the model's owner, user, or others. Despite the efforts of measuring these risks via benchmarks and…

Cryptography and Security · Computer Science 2025-06-04 David Piorkowski , Michael Hind , John Richards , Jacquelyn Martino

In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is acceptable. This…

Artificial Intelligence · Computer Science 2022-02-14 Michael Kläs , Lisa Jöckel , Rasmus Adler , Jan Reich

We propose a model-agnostic framework for short-term occupational accident forecasting that leverages safety inspections and models accident occurrences as binary time series. The approach generates daily predictions, which are then…

Machine Learning · Computer Science 2025-12-30 Aho Yapi , Pierre Latouche , Arnaud Guillin , Yan Bailly

In the following writing we discuss a conceptual framework for representing events and scenarios from the perspective of a novel form of causal analysis. This causal analysis is applied to the events and scenarios so as to determine…

Artificial Intelligence · Computer Science 2018-07-06 Anton Kolonin

This paper introduces a general simulation framework that can allow the simulation of crashes and the evaluation of consequences on existing microsimulation packages. A specific family of simple and reproducible conflict indicators is…

Multiagent Systems · Computer Science 2018-08-07 Vittorio Astarita , Vincenzo Pasquale Giofré

We propose two types of Quantile Graphical Models (QGMs) --- Conditional Independence Quantile Graphical Models (CIQGMs) and Prediction Quantile Graphical Models (PQGMs). CIQGMs characterize the conditional independence of distributions by…

Statistics Theory · Mathematics 2019-10-29 Alexandre Belloni , Mingli Chen , Victor Chernozhukov

This paper presents the first application of Gaussian Mixture Copula Models to the statistical modeling of driving scenarios for the safety validation of automated driving systems. Knowledge of the joint probability distribution of scenario…

Robotics · Computer Science 2026-01-27 Christian Reichenbächer , Philipp Rank , Jochen Hipp , Oliver Bringmann

Classical machine learning techniques often struggle with overfitting and unreliable predictions when exposed to novel conditions. Introducing causality into the modelling process offers a promising way to mitigate these challenges by…

Computational Engineering, Finance, and Science · Computer Science 2025-05-28 David Zapata Gonzalez , Marcel Meyer , Oliver Mueller
‹ Prev 1 8 9 10 Next ›