Generation models for robotics.
Yandong Wang, Jiaqian Yu, Xiongfeng Peng et al. · arXiv preprint · Jun 2026
Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end...
Yandong Wang, Jiaqian Yu, Xiongfeng Peng et al. · arXiv preprint · Jun 2026
Vision-language-action (VLA) models show strong capabilities in single and dual-arm robotic manipulation. Prior works show coordinated bimanual behaviors can emerge from end-to-end...
Yu Zhang, Kangyi Ji, Yongxiang Zou et al. · arXiv preprint · Jun 2026
This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observati...
Yu Zhang, Kangyi Ji, Yongxiang Zou et al. · arXiv preprint · Jun 2026
This paper presents an invertible neural network adapter for general robotic manipulation, designed to generate precise high-dimensional actions conditioned on multimodal observati...
William English, Hao Zheng, Rickard Ewetz · arXiv preprint · Jul 2026
Vision-Language-Action (VLA) models have demonstrated promising generalization capabilities across robotic manipulation tasks, yet their real-world deployment remains limited by th...
Siqiao Huang, Kun-Ying Lee, Dongming Qiao et al. · arXiv preprint · Jun 2026
Humanoid whole-body control has made significant progress in recent years, yet existing approaches remain limited to few-skill policies with heavy reward engineering, or motion trackers that are difficult to extend to new input modalities. We argue that the key to general-purpose humanoid control is...
Arunim Joarder, Arjun Bhardwaj, René Zurbrügg et al. · IROS 2026 · Jun 2026
Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model ...
Arunim Joarder, Arjun Bhardwaj, René Zurbrügg et al. · IROS 2026 · Jun 2026
Tactile sensing provides direct measurements of contact interactions that are essential for robotic manipulation. However, current simulators lack the fidelity to faithfully model ...
Yuquan Xue, Le Xu, Zeyi Liu et al. · arXiv preprint · Jul 2026
Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond t...
Read these papers in order to build expertise in generation.
Yandong Wang, Jiaqian Yu et al. · 2026
Yandong Wang, Jiaqian Yu et al. · 2026
Yu Zhang, Kangyi Ji et al. · 2026
Yu Zhang, Kangyi Ji et al. · 2026
William English, Hao Zheng et al. · 2026
Siqiao Huang, Kun-Ying Lee et al. · 2026
…and 3 more papers.
