Related papers: Steering Awareness: Detecting Activation Steering …
While trajectory prediction plays a critical role in enabling safe and effective path-planning in automated vehicles, standardized practices for evaluating such models remain underdeveloped. Recent efforts have aimed to unify dataset…
Active inference has emerged as an alternative approach to control problems given its intuitive (probabilistic) formalism. However, despite its theoretical utility, computational implementations have largely been restricted to…
Sensor visibility is crucial for safety-critical applications in automotive, robotics, smart infrastructure and others: In addition to object detection and occupancy mapping, visibility describes where a sensor can potentially measure or is…
Inspired by the concept of active learning, we propose active inference$\unicode{x2013}$a methodology for statistical inference with machine-learning-assisted data collection. Assuming a budget on the number of labels that can be collected,…
We investigate the application of active inference in developing energy-efficient control agents for manufacturing systems. Active inference, rooted in neuroscience, provides a unified probabilistic framework integrating perception,…
Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…
Novelty detection is crucial for real-life applications. While it is common in activity recognition to assume a closed-set setting, i.e. test samples are always of training categories, this assumption is impractical in a real-world…
Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…
Neural network classifiers trained on datasets with uneven group representation often inherit class biases and learn spurious correlations. These models may perform well on average but consistently fail on atypical groups. For example, in…
Event cameras are bio-inspired vision sensors that naturally capture the dynamics of a scene, filtering out redundant information. This paper presents a deep neural network approach that unlocks the potential of event cameras on a…
Connecting multiple machine learning models into a pipeline is effective for handling complex problems. By breaking down the problem into steps, each tackled by a specific component model of the pipeline, the overall solution can be made…
Distribution grids currently lack comprehensive real-time metering. Nevertheless, grid operators require precise knowledge of loads and renewable generation to accomplish any feeder optimization task. At the same time, new grid…
To control the behavior of language models, steering methods attempt to ensure that outputs of the model satisfy specific pre-defined properties. Adding steering vectors to the model is a promising method of model control that is easier…
The goal of an Intrusion Detection is inadequate to detect errors and unusual activity on a network or on the hosts belonging to a local network by monitoring network activity. Algorithms for building detection models are broadly classified…
Environment perception is the task for intelligent vehicles on which all subsequent steps rely. A key part of perception is to safely detect other road users such as vehicles, pedestrians, and cyclists. With modern deep learning techniques…
It is widely acknowledged that drivers should remain in the control loop of automated vehicles before they completely meet real-world operational conditions. This paper introduces an `indirect shared control' scheme for steer-by-wire…
The field of mechanistic interpretability in pre-trained transformer models has demonstrated substantial evidence supporting the ''linear representation hypothesis'', which is the idea that high level concepts are encoded as vectors in the…
Active inference is a mathematical framework which originated in computational neuroscience as a theory of how the brain implements action, perception and learning. Recently, it has been shown to be a promising approach to the problems of…
Human emotion detection in automated vehicles helps to improve comfort and safety. Research in the automotive domain focuses a lot on sensing drivers' drowsiness and aggression. We present a new form of implicit driver-vehicle cooperation,…
The ability to selectively attend to relevant stimuli while filtering out distractions is essential for agents that process complex, high-dimensional sensory input. This paper introduces a model of covert and overt visual attention through…