Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
About this episode
The episode discusses the Xiaomi-Robotics-1 model, which utilizes over 100K hours of real-world data to enhance mobile manipulation tasks through vision-language-action capabilities.
🤗 Upvotes: 57 | cs.RO, cs.CV Authors: Xiaomi Robotics Team, Jun Guo, Piaopiao Jin, Jason Li, Peiyan Li, Yingyan Li, Futeng Liu, Wanli Peng, Optimus Qin, Yifei Su, Nan Sun, Qiao Sun, Runze Suo, Heyun Wang, Yunhong Wang, Rujie Wu, Caoyu Xia, Lina Zhang, Jack Zhao, Guoliang Chen, Wenlong Chen, Xinze He, Bin Li, Qing Li, Zhuorong Li, Heng Qu, Wenxuan Song, Diyun Xiang, Yifan Xie, Peiran Xu, Hangjun Ye, Wen Ye, Han Zhao, Quanyun Zhou Title: Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories Arxiv: http://arxiv.org/abs/2607.15330v1 Abstract: We present Xiaomi-Robotics-1, a foundational vision-language-action (VLA) model capable of (1) following diverse language instructions to perform a wide range of mobile manipulation tasks in unseen environments out-of-the-box, and (2) efficiently adapting to novel downstream tasks with minimal fine-tuning data. We propose a two-stage training recipe consisting of pre-training and post-training. During pre-training, we imbue the model with broad and generalizable action-generation capabilities by training on over 100k hours of real-world manipulation trajectories collected via UMI devices…
More episodes of Daily Paper Cast
- RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
- RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM
- Loop the Loopies!
- xHC: Expanded Hyper-Connections
- Cura 1T: Specialized Model for Agentic Healthcare
- On-Policy Delta Distillation
Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.