A Progressive Training Strategy for Embodied Vision-Language Models to Mitigate Spatio-Temporal Hallucinations

arXiv:2604.10506 · cs.AI · Submitted 2026-04-12 · Read on arXiv

cs.AI

Submitted: 2026-04-12

Updated: 2026-09-07

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Sources

Related papers