ByteDance Seed · 字节跳动 Seed
Embodied / robotics model — runs on robot hardware, not a token API. No per-1M pricing. For API-priced LLMs see the model catalog.
| Creator | ByteDance Seed (字节跳动 Seed) |
| Architecture | Vision-Language-Action (VLA) |
| Embodiment | Bimanual dexterous hands |
GR-Dexter is ByteDance Seed's holistic hardware-model-data framework for generalist manipulation on a bimanual dexterous-hand robot. It targets the specific challenge of scaling vision-language-action models to high-degree-of-freedom dexterous hands — where most VLA work stops at simpler grippers. Part of ByteDance's broader GR robotics research line.
Dexterous (high-DoF) manipulation research; teams working on multi-finger hands rather than parallel grippers.
Your brand here — Reach our audience of professional directory owners and boost your sales.