3 papers
cs.AI2026
MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft
Jianxin Gao, Beini Hu, Runze Li +6
With the prosperity of the large language models (LLMs), it has become an interesting topic: how do LLM-based agents work in Minecraft? Unfortunately, most existing benchmarks eval…
cs.RO2025
GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
Yunfei Li, Xiao Ma, Jiafeng Xu +18
We present GR-RL, a robotic learning framework that turns a generalist vision-language-action (VLA) policy into a highly capable specialist for long-horizon dexterous manipulation.…
cs.RO2025
GR-3 Technical Report
Chilam Cheang, Sijin Chen, Zhongren Cui +18
We report our recent progress towards building generalist robot policies, the development of GR-3. GR-3 is a large-scale vision-language-action (VLA) model. It showcases exceptiona…