DreamVu Publishes PRISM: A Multi-View Retail Video Dataset for Embodied AI Research
DreamVu today released PRISM, a 270,000-sample multi-view video dataset collected across five real supermarkets for training and evaluating vision-language models on embodied AI tasks. Fine-tuning on PRISM reduces average error rates by 66.6% and cuts embodied reasoning errors by a factor of five compared to general-purpose baselines, across 20 capability probes evaluated in the accompanying paper.
