Related papers: The Constitutional Filter: Bayesian Estimation of …
Recent work has uncovered close links between between classical reinforcement learning algorithms, Bayesian filtering, and Active Inference which lets us understand value functions in terms of Bayesian posteriors. An alternative, but less…
As frontier AI models are deployed in high-stakes decision pipelines, their ability to maintain metacognitive stability (knowing what they do not know, detecting errors, seeking clarification) under adversarial pressure is a critical safety…
The gap between our ability to collect interesting data and our ability to analyze these data is growing at an unprecedented rate. Recent algorithmic attempts to fill this gap have employed unsupervised tools to discover structure in data.…
Federated learning's poor performance in the presence of heterogeneous data remains one of the most pressing issues in the field. Personalized federated learning departs from the conventional paradigm in which all clients employ the same…
Learning-based methods commonly treat state estimation in robotics as a sequence modeling problem. While this paradigm can be effective at maximizing end-to-end performance, models are often difficult to interpret and expensive to train,…
Recent years have seen an increasing amount of work on embodied AI agents that can perform tasks by following human language instructions. However, most of these agents are reactive, meaning that they simply learn and imitate behaviors…
Understanding and modeling animal behavior is essential for studying collective motion, decision-making, and bio-inspired robotics. Yet, evaluating the accuracy of behavioral models still often relies on offline comparisons to static…
This chapter introduces a conceptual framework for qualitative risk assessment of AI, particularly in the context of the EU AI Act. The framework addresses the complexities of legal compliance and fundamental rights protection by itegrating…
What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execution with persistent organizational knowledge learned from…
Automated eligibility systems increasingly determine access to essential public benefits, but the explanations they generate often fail to reflect the legal rules that authorize those decisions. This thesis develops a legally grounded…
Ensuring trustworthiness in machine learning -- by balancing utility, fairness, and privacy -- remains a critical challenge, particularly in representation learning. In this work, we investigate a family of closely related…
Recognising the goals or intentions of observed vehicles is a key step towards predicting the long-term future behaviour of other agents in an autonomous driving scenario. When there are unseen obstacles or occluded vehicles in a scenario,…
Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinders their confident deployment in real-world safety-critical…
Data-driven models based on deep learning algorithms intend to overcome the limitations of traditional constitutive modelling by directly learning from data. However, the need for extensive data that collate the full state of the material…
Camouflaged object detection (COD) and camouflaged instance segmentation (CIS) aim to recognize and segment objects that are blended into their surroundings, respectively. While several deep neural network models have been proposed to…
Determining subgroups that respond especially well (or poorly) to specific interventions (medical or policy) requires new supervised learning methods tailored specifically for causal inference. Bayesian Causal Forest (BCF) is a recent…
Artificial intelligence systems have achieved remarkable capability in natural language processing, perception and decision-making tasks. However, their behaviour often remains opaque and difficult to verify, limiting their applicability in…
Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameters need a rapid strategic search through active learning such as Bayesian…
This article discusses the evolving role of artificial intelligence (AI) in the legal profession, focusing on its potential to streamline tasks such as document review, research, and contract drafting. However, challenges persist,…
High-performance catalysts are crucial for sustainable energy conversion and human health. However, the discovery of catalysts faces challenges due to the absence of efficient approaches to navigating vast and high-dimensional structure and…