Research Highlights
DreamVu Research is bridging the knowledge gap for physical AI, creating the high-fidelity datasets required for the next generation of humanoid robots and embodied agents.
NEW · MAY 2026 SABER PAPER

SABER: A Scalable Action-Based Embodied Dataset for Real-World VLA Adaptation.

The first high-fidelity retail robotics action dataset built from natural human behavior, not teleoperation.

The Impact

Domain-specific robot deployment is fundamentally a data problem. SABER demonstrates that human video — systematically captured and retargeted — is a scalable foundation for robot adaptation, achieving 2.19X improvement over baselines.

44.8K
Training Samples
100+
Hours Captured
91%
Fridge Task Success Rate
PUBLISHED · MARCH 2026 PRISM PAPER

PRISM: Unifying physical AI knowledge across space, physics, and embodied action.

Bridging the reasoning-action gap for VLMs in real-world environments.

The Impact

PRISM provides the structural bridge between visual understanding and physical execution, reducing average error rates by 66.6% across embodied reasoning tasks.

66.6%
Error reduction
270K
Samples
Reasoning Performance Gain