相关论文: Multi-Dimensional Model Integrity and Responsibili…
We introduce Interactive Intelligence, a novel paradigm of digital human that is capable of personality-aligned expression, adaptive interaction, and self-evolution. To realize this, we present Mio (Multimodal Interactive Omni-Avatar), an…
Large Language Models (LLMs) are increasingly used in settings where reliable self-assessment is critical. Assessing model reliability has evolved from using probabilistic correctness estimates to, more recently, eliciting verbalized…
AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great…
Mutual Information (MI) is a fundamental metric for quantifying dependency between two random variables. When we can access only the samples, but not the underlying distribution functions, we can evaluate MI using sample-based estimators.…
The increasing integration of artificial intelligence (AI) into medical diagnostics necessitates a critical examination of its ethical and practical implications. While the prioritization of diagnostic accuracy, as advocated by Sabuncu et…
Understanding how LLMs reason is hindered by a practical asymmetry: while their generated outputs are observable, the underlying reasoning patterns remain opaque. Relying on single probes, such as Mutual Information Peak (MIP) or…
Increased adoption of artificial intelligence (AI) systems into scientific workflows will result in an increasing technical debt as the distance between the data scientists and engineers who develop AI system components and scientists,…
Spatial perception and reasoning are core components of human cognition, encompassing object recognition, spatial relational understanding, and dynamic reasoning. Despite progress in computer vision, existing benchmarks reveal significant…
As the deployment of Artificial Intelligence (AI) systems in high-stakes sectors - like healthcare, finance, education, justice, and infrastructure has increased - the possibility and impact of failures of these systems have significantly…
Tabular anomaly detection is often handled by single detectors or static ensembles, even though strong performance on tabular data typically comes from heterogeneous model families (e.g., tree ensembles, deep tabular networks, and tabular…
Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…
This paper presents a systematic review of the literature on evaluation criteria for Trustworthy Artificial Intelligence (TAI), with a focus on the seven EU principles of TAI. This systematic literature review identifies and analyses…
More recently, Explainable Artificial Intelligence (XAI) research has shifted to focus on a more pragmatic or naturalistic account of understanding, that is, whether the stakeholders understand the explanation. This point is especially…
Artificial Intelligence (AI) is transforming sectors such as healthcare, finance, and autonomous systems, offering powerful tools for innovation. Yet its rapid integration raises urgent ethical concerns related to data ownership, privacy,…
We propose MIRA, a new benchmark designed to evaluate models in scenarios where generating intermediate visual images is essential for successful reasoning. Unlike traditional CoT methods that rely solely on text, tasks in MIRA require…
This paper claims that machine learning models deployed in high stakes domains such as medicine must be interpretable, shareable, reproducible and accountable. We argue that these principles should form the foundational design criteria for…
Safety and responsibility evaluations of advanced AI models are a critical but developing field of research and practice. In the development of Google DeepMind's advanced AI models, we innovated on and applied a broad set of approaches to…
Explainable Artificial Intelligence (XAI) techniques are used to provide transparency to complex, opaque predictive models. However, these techniques are often designed for image and text data, and it is unclear how fit-for-purpose they are…
Deep Learning (DL) models processing images to recognize the health state of large infrastructure components can exhibit biases and rely on non-causal shortcuts. eXplainable Artificial Intelligence (XAI) can address these issues but…
Reliable inference requires that artificial intelligence (AI) models provide trustworthy uncertainty estimates, not merely accurate predictions. Recent advances in Bayesian learning have made significant progress toward this goal, and…