2 papers
cs.CV2026
Sim2real Image Translation Enables Viewpoint-Robust Policies from Fixed-Camera Datasets
Jeremiah Coholich, Justin Wit, Robert Azarcon +1
Vision-based policies for robot manipulation have achieved significant recent success, but are still brittle to distribution shifts such as camera viewpoint variations. Robot demon…
cs.CV2025
MAPS: Preserving Vision-Language Representations via Module-Wise Proximity Scheduling for Better Vision-Language-Action Generalization
Chengyue Huang, Mellon M. Zhang, Robert Azarcon +2
Vision-Language-Action (VLA) models inherit strong priors from pretrained Vision-Language Models (VLMs), but naive fine-tuning often disrupts these representations and harms genera…