相关论文: Steering Awareness: Detecting Activation Steering …

Speculative decoding accelerates language model inference by separating generation into fast drafting and parallel verification. Its main limitation is drafter-verifier misalignment, which limits token acceptance and reduces overall…

Steering feedback plays a substantial role in the validity of driving simulators for the virtual development of modern vehicles. Established objective steering characteristics typically assess the feedback behavior in the frequency range of…

We analyze the observability of motion estimates from the fusion of visual and inertial sensors. Because the model contains unknown parameters, such as sensor biases, the problem is usually cast as a mixed identification/filtering, and the…

Annotated driving scenario trajectories are crucial for verification and validation of autonomous vehicles. However, annotation of such trajectories based only on explicit rules (i.e. knowledge-based methods) may be prone to errors, such as…

Modeling perception sensors is key for simulation based testing of automated driving functions. Beyond weather conditions themselves, sensors are also subjected to object dependent environmental influences like tire spray caused by vehicles…

Active perception has been employed in many domains, particularly in the field of robotics. The idea of active perception is to utilize the input data to predict the next action that can help robots to improve their performance. The main…

Vehicle platooning has been a promising solution for improving traffic efficiency and throughput. However, a failure in a single vehicle, including communication loss with neighboring vehicles, can significantly disrupt platoon performance…

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Concept-based explanation methods, such as Concept Activation Vectors, are potent means to quantify how abstract or high-level characteristics of input data influence the predictions of complex deep neural networks. However, applying them…

Application of deep learning to enhance the accuracy of intrusion detection in modern computer networks were studied in this paper. The identification of attacks in computer networks is divided in to two categories of intrusion detection…

Autonomous driving presents a complex challenge, which is usually addressed with artificial intelligence models that are end-to-end or modular in nature. Within the landscape of modular approaches, a bio-inspired neural circuit policy model…

Road traffic accidents remain a significant global concern, with human error, particularly distracted and impaired driving, among the leading causes. This study introduces a novel driver behaviour classification system that uses external…

The training of many existing end-to-end steering angle prediction models heavily relies on steering angles as the supervisory signal. Without learning from much richer contexts, these methods are susceptible to the presence of sharp road…

Sparse Autoencoders (SAEs) are increasingly used to interpret foundation models, but their role as an actionable intervention space remains less understood, especially in vision. We study whether sparse visual features can be used not only…

With exponential increase in the availability oftelemetry / streaming / real-time data, understanding contextualbehavior changes is a vital functionality in order to deliverunrivalled customer experience and build high performance andhigh…

The evolution of Intelligent Transportation System in recent times necessitates the development of self-driving agents: the self-awareness consciousness. This paper aims to introduce a novel method to detect abnormalities based on internal…

Jailbreak prompts can trigger harmful completions on aligned LLMs, In accordance, safety steering has been proposed: test-time activation interventions that steer jailbreak activations to trigger refusal while preserving benign utility.…

The application of computer vision is gradually increasing across various domains. They employ deep learning models with a black-box nature. Without the ability to explain the behavior of neural networks, especially their decision-making…

Vision-based Transformer have shown huge application in the perception module of autonomous driving in terms of predicting accurate 3D bounding boxes, owing to their strong capability in modeling long-range dependencies between the visual…

Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software.Most existing inference approaches assume access to code to collect execution sequences. In…