News
News and press releases.
Announcements, research milestones, and media coverage. Papers and datasets are on the Research page.
July 2, 2026
DreamVu Research on NVIDIA’s Cosmos3 Overturns a Core Assumption in Robot Training — The Overlooked Camera Angle Beats More Data
First-person video has dominated embodied AI research. Adapting NVIDIA’s Cosmos3-Nano world model, DreamVu’s new study shows that a single wide-view camera watching the whole scene matched or beat training on all data combined — using half the footage.
Read release →May 12, 2026
DreamVu’s SABER Dataset Delivers 2.19× Performance Gain on NVIDIA GR00T — Captured From Real Stores, Not Simulators
Real-world human capture more than doubles humanoid manipulation success on retail benchmark, outpacing simulation-only fine-tuning of NVIDIA GR00T N1.6 by 2.19×.
Read release →April 28, 2026
DreamVu Launches the Largest Grocery SimReady Asset Library — Built from Real-World Capture
2,200 SimReady USD assets captured from real-world environments with lab-measured physics — the first grocery simulation library built from reality, not artist approximation. Ready for NVIDIA Isaac Sim, Cosmos, and GR00T workflows.
Read release →April 5, 2026
DreamVu Publishes PRISM: A Multi-View Retail Video Dataset for Embodied AI Research
270,000-sample dataset covering spatial, physical, and embodied action reasoning reduces error rates by 66.6% on 20 capability probes; 100K open subset and fine-tuned model weights released on Hugging Face.
Read release →Tell us what your model needs to learn.
Capture programs, research collaboration, and dataset partnerships.