Lumo 2 Context

Audience

Developers

Workflow

latent world-action model

Specifications

• System Type: Latent world-action robotics foundation model
• Training Pipeline: Three-stage progressive modality pre-alignment and joint training
• Control Scope: Predictive latent-dynamics robot control
• Training Data Source: Vision-language corpora; egocentric human video; multi-robot demonstrations
• Supported Platforms: Cross-embodiment robot platforms and human-to-robot transfer
• Evaluation Mode: Embodied benchmarks and real-world manipulation
• Tasks Demonstrated: Pick-and-place, temporal reasoning, long-horizon and dexterous manipulation
• Release Model: Research technical report

Tags

• Peer Group: Robot manipulation foundation model, Robot foundation model

Comparable Systems

• Being-H0.8 - BeingBeyond - Robotics Foundation Model
• Helix - Figure AI - Robotics Foundation Model
• FusionMax - Muks Robotics AI Pvt. Ltd. - Robotics Foundation Model
• GEN-1 - Generalist - Software
• Lumo-1 - Astribot - Robotics Foundation Model
• Rho-alpha - Microsoft - Robotics Foundation Model
• DYNA-1 - Dyna Robotics - Robotics Foundation Model