KyutaiREKI
REKI 2B RoboTwin Clean
This dual-arm AgileX ALOHA policy trains on the clean scenes of 50 RoboTwin tasks. Randomized scenes are a distribution-shift evaluation for this checkpoint.
Research release
Register tokens carry recent visual context
REKI stores 32 tokens per frame across three frames one second apart. The action expert can use this recent history. The repository separates raw and moving-average weights; the documented fine-tuning path starts with raw weights.reki-2b-robotwin-clean: Kyutai model card
Specifications & access
| Detail | Value and conditions |
|---|---|
| Status | Research release |
| Access | Downloadable |
| Model identifiers | kyutai/reki-2b-robotwin-clean |
| Developers | Kyutai, Inria and École nationale des ponts et chaussées.reki-2b-robotwin-clean: Kyutai model card |
| Actual size | 2.4B parameters: a 2.2B vision-language component and 0.2B action expert.reki-2b-robotwin-clean: Kyutai model card |
| Ancestry and license | Qwen 3.5 2B; CC BY-NC-SA 4.0 weights and MIT code.reki-2b-robotwin-clean: Kyutai model card |
Related models
A Qwen-based vision-language-action model pretrained on robot, simulation, human-hand and vision-language data.
Launch date not confirmedResearch releaseDownloadable