28 papers
Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment
Boyuan Wang, Zhenyuan Zhang, Zhiqin Yang +16
Zero2Skill is a robot learning system that autonomously collects, verifies, and resets manipulation data while using a large language model to store and reuse human corrections, dr…
GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch
GigaWorld Team, Angen Ye, Angyuan Ma +26
The paper introduces GigaWorld-Policy-0.5, a robot control model that learns from future visual dynamics during training but generates actions only at inference, achieving faster (…
HALO-WA: Hybrid-Attention Latent-Guided Online Reinforcement Learning for World-Action Models
Angen Ye, Weijie Ke, Xiaofeng Wang +7
World-action (WA) models can generate long-horizon action chunks for general-purpose robotic manipulation, but they remain vulnerable to calibration, perception, and contact-dynami…
GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation
GigaWorld Team, Angyuan Ma, Boyuan Wang +24
Evaluating embodied robot foundation models remains a critical bottleneck; unlike large language models efficiently assessed via digital benchmarks, robotic policies require slow,…
Spatial-Aware Reduction Framework: Towards Efficient and Faithful Visual State Space Models
Jindi Lv, Aoyu Li, Yuhao Zhou +6
Mamba demonstrates strong efficiency in modeling long visual sequences. However, when token reduction is applied to structurally enhanced Mamba variants, these models exhibit a sev…
R2RDreamer: 3D-aware Data Augmentation for Spatially-generalized 2D Manipulation Policies
Xiuwei Xu, Haowen Sun, Angyuan Ma +7
Spatial generalization is critical for imitation-learned manipulation policies, but achieving it typically requires scaling demonstrations across diverse object poses, robot config…