3 papers
cs.CL2026
Contextual Linear Activation Steering of Language Models
Brandon Hsu, Daniel Beaglehole, Adityanarayanan Radhakrishnan +1
Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited labeled data. While effectiv…
cs.CV2021
Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Prediction
Arnav V. Malawade, Shih-Yuan Yu, Brandon Hsu +3
In autonomous vehicles (AVs), early warning systems rely on collision prediction to ensure occupant safety. However, state-of-the-art methods using deep convolutional networks eith…
cs.CV2021
roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs
Arnav Vaibhav Malawade, Shih-Yuan Yu, Brandon Hsu +3
Recently, road scene-graph representations used in conjunction with graph learning techniques have been shown to outperform state-of-the-art deep learning techniques in tasks inclu…