Browse and export your curated research paper collection
Bryce Grant, Xijia Zhao, Peng Wang 3/19/2026 arxiv
machine learningVision-Language-Action (VLA) models combine perception, language, and motor control in a single architecture, yet how they translate multimodal inputs into actions remains poorly understood. We apply activation injection, sparse autoencoders (SAEs), and linear probes to six models spanning 80M--7B p...
Preparing your export...