3 papers
cs.RO2026
IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies
Kian Hosseinkhani, Qinhe Peng, George Shramko +6
Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedic…
cs.CV2026
P-CORE: Self-Supervised Surface Consistency for Point-Based Neural Editing
Yanshu Zhang, Shichong Peng, Mehran Aghabozorgi +2
Advances in neural rendering have enabled high-fidelity multi-view reconstruction of 3D scenes. However, free-form non-rigid shape editing remains a significant challenge. Point-ba…
cs.LG2026
WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Control
Mehran Aghabozorgi, Alireza Moazeni, Yanshu Zhang +1
Model-based reinforcement learning promises strong sample efficiency but often underperforms in practice due to compounding model error, unimodal world models that average over mul…