Product profile
GEN-0
GEN-0 is Generalist's predecessor embodied foundation-model generation, trained on large-scale real-world manipulation data and designed to transfer across...
Facts
- Company
- Generalist
- Product type
- software
- Status
- historical
- Primary capability
- Cross-embodiment manipulation from physical-interaction pretraining
- Website
- https://generalistai.com/blog/gen-0
About GEN-0
GEN-0 is Generalist’s embodied foundation-model generation for multimodal training on raw physical interaction. Harmonic Reasoning interleaves asynchronous, continuous-time streams of sensing and acting tokens, allowing the model to coordinate perception and control across different robot embodiments.
Generalist tested GEN-0 on 6-DoF, 7-DoF and 16-plus-DoF semi-humanoid robots and scaled the family beyond 10 billion parameters. The company reports pretraining on more than 270,000 hours of real-world manipulation data spanning homes, warehouses and workplaces, with downstream tasks including assembly, packing, clothing handling and food preparation.
Market context
verified exact official high-quality product visual, embodied_foundation_model, Robotics Foundation Model, existing_category_first, https://generalistai.com/assets/pages/blog/gen-0/assets/generalist-gen0-og.png, 2026-08-20, https://generalistai.com/blog/gen-0, official_first_party_model_diagram, 2026-08-19, developer_platform, 2026-08-19, exact_official_model_visual, Robotics Foundation Model, developer_platform, 2026-08-21, resolved_to_canonical_category, embodied_foundation_model, developer_platform
Summary
Type: Robotics foundation model
Core: Physical-interaction pretraining
Function: Learn manipulation policies across embodiments
Audience: Embodied-AI and robotics teams
Specifications
- data_growth_rate
- More than 10,000 new hours per week hours/week
- pretraining_data
- More than 270,000 hours of real-world manipulation data hours
- reasoning_architecture
- Harmonic Reasoning with asynchronous continuous-time sensing and acting tokens
- reported_model_scale
- Scaled beyond 10 billion parameters billion_parameters
- tested_embodiments
- 6-DoF; 7-DoF; 16+ DoF semi-humanoid robots
Operations
- Environment
- homes, warehouses, workplaces, robotics_research
- Primary user
- robotics_researchers, embodied_ai_teams
- Role
- general_manipulation, cross_embodiment_control, sensorimotor_reasoning
- Interaction model
- model_inference, post_training, closed_loop_robot_policy
- Mobility class
- software_only
- Product detail
- verified exact official high-quality product visual, embodied_foundation_model, Robotics Foundation Model, existing_category_first, https://generalistai.com/assets/pages/blog/gen-0/assets/generalist-gen0-og.png, 2026-08-20, https://generalistai.com/blog/gen-0, official_first_party_model_diagram, 2026-08-19, developer_platform, 2026-08-19, exact_official_model_visual, Robotics Foundation Model, developer_platform, 2026-08-21, resolved_to_canonical_category, embodied_foundation_model, developer...
Research, Articles and recent verified events
- Generalist releases GEN-1.5 with one-shot physical-task learning — 2026-08-19
- Generalist reports up to 10–20× gains in GEN-1 actuator adaptation — 2026-08-04
- Generalist AI validates GEN-1 on Elite Robots cobot platform — 2026-07-21
- Generalist AI raises $400M at $2B valuation for robotics foundation models — 2026-06-04
- Generalist AI releases GEN-1, a general-purpose robotics AI model achieving 99% success rates on physical tasks — 2026-04-02
- Generalist gives first public live demo of GEN-0 at NVIDIA GTC — 2026-03-24
- Generalist publishes physical commonsense research update — 2026-01-29
- Generalist introduces GEN-0 embodied foundation model — 2025-11-04