Grounded and Faithful Vision-Language Models for Real-World Deployment

The workshop studies whether vision-language and action models reliably connect their outputs to visual and physical evidence. Research addresses grounding, hallucinations, consistent reasoning and behaviour under changing conditions, including methods and benchmarks for dependable multimodal deployment. Session: 08:00–17:00 (Australia/Sydney). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.