CogACT
Componentized VLA with specialized diffusion action module
CogACT separates thinking from doing — the language model figures out what to do, and a specialized diffusion model handles the precise physical movements. This split makes it especially good at tasks needing fine motor control.
Primarily a research model. Requires significant ML experience to set up and operate. Best suited for labs with existing robotics infrastructure.
A componentized Vision-Language-Action architecture using DiT-Large as its action module, conditioned on VLM outputs for precise manipulation.
Open X-Embodiment + proprietary manipulation data
Precision screw insertion on assembly line
Baseline for fine-grained manipulation benchmarks
Careful handling of fragile items
Serious GPU and ML engineering required
RELATED DISCUSSIONS
Community →Seeded and planned prompts — not live forum activity yet.
- Community signalIntermediate / AdvancedHow should EAR track open robotics models?
Meta-discussion on ontology, benchmarks, and graph links for open-weight VLAs and manipulation models.
- Community signalIntermediate / AdvancedOpenVLA in the field — what breaks first?
Open Models room prompt linked to openvla-7b — inference, fine-tuning, and sim-to-real gaps. Seeded prompt only.
Related Models
VIEW ALL →OpenVLA
State-of-the-art open-source VLA for robot manipulation
Diffusion Policy
Visuomotor policy learning via conditional diffusion
Octo
Generalist robot policy trained on 800K trajectories