Finds 98% of hands in first-person video it was never trained on, with about 60% fewer missed hands than two leading open models.
Read more →Every scene is a real place, delivered as 16K color, metric depth at every pixel, and dense point clouds — the color and geometry of the same instant, from the same optics, across the entire 360° view.
Read more →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 more →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 more →270,000-sample dataset covering spatial, physical, and embodied action reasoning reduces error rates by 66.6% on 20 capability probes.
Read more →