Robot AI model
DexVLA
DexVLA attaches a separately pretrained diffusion action expert to a vision-language backbone. The paper studies an embodiment curriculum across single-arm, bimanual and dexterous-hand manipulation; the repository publishes code and pretrained action-expert components.
Records last verified Oct 13, 2026 · Send a correction
- Type
- VLA
- Released / introduced
- Feb 9, 2025
- Public weights
- Not established
- Licence / scope
- Not established
- Parameters
- Not disclosed
- Base model
- Qwen2-VL-2B
- Humanoid association
- None reported
- Inputs
- vision, language
- Outputs
- continuous robot action chunks
Release dates can mark an announcement or paper introduction. Public checkpoints, code licences and weight terms are distinct; follow the publisher’s links for the stated scope.
More robot AI models
Evidence
Sources
- [s1] DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control ↗
DexVLA research team · paper · published Feb 9, 2025 · accessed Oct 13, 2026
- [s2] DexVLA official repository: affiliations, backbone and action-expert release ↗
Midea AI · official · accessed Oct 13, 2026