Few Contrastive Attention Heads Enable Visual Grounding in Large Vision-Language Models

Neha Sengar, Andres Saurez, Dongsoo Har, Sangkeum Lee

Transactions on Machine Learning Research (TMLR) (Featured at NeurIPS 2026), 2026

Perturbation-Based Uncertainty for Failure Detection in Vision-Language-Action Models

Yousung Lee, Dongsoo Har

Robotics: Science and Systems (RSS) Workshop on Trustworthy Embodied Foundation Models (Oral Presentation), 2026

Vision-Based Tire Lifting for Parking by Dual Parking Robot

Neha Sengar, Yousung Lee, Kuk Won Ko, Dongsoo Har, Sangkeum Lee

IEEE Sensors Journal, 2026