YAM robotic arm family — YAM, YAM Pro, YAM Ultra, BIG YAM

Hardware for embodied intelligence

The physical building blocks for the embodied intelligence era.

Research published on the YAM platform

Scalable Behavior Cloning with Open Data, Training, and Evaluation
UC Berkeley · Amazon FAR · XDOF 2026
MolmoAct 2: An Open Foundation for Robots that Work in the Real World
Allen Institute for AI 2026
DreamZero: World Action Models are Zero-shot Policies
NVIDIA 2026
SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
Stanford · UC Berkeley 2025
SARM2: Multi-Task Stage-Aware Reward Modeling for Self-Improving Robotic Manipulation
Stanford · UC Berkeley · Shanghai Jiao Tong · XDOF 2026
ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
NVIDIA 2026
Self-Improving Vision-Language-Action Models via Residual RL
Academic research 2025
SoftMimicGen: Scalable Robot Learning for Deformable Object Manipulation
NVIDIA 2026
Raiden: A Policy Learning Toolkit for YAM Bimanual Robot Arms
Toyota Research Institute 2026

Ready to build with YAM?

Explore products