3

When Listening Becomes Easier: Scrubbing Visual Cues for Shortcut-Free VLAs
Scrubbing visual cues for shortcut-free vision-language-action models.
Jasper Gerigk, Kenzo Aspuru-Takata, Chin-Hsuan Wu, Mohammad Mohammadi, Shuhong Zheng, Igor Gilitschenski
PDF Abstract
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Sparse-context on-policy self-distillation for efficient vision-language models.
Ahmadreza Jeddi, Enming Zhang, Jasper Gerigk, Hakki Karaimer, Mozhgan Nasr Azadani, Jiayun Luo, Minh Ngoc Le, Gholamali Aminian, Hugo Buurmeijer, Yongchao Chen, Leonid Sigal, Igor Gilitschenski, Konstantinos G. Derpanis, Marco Pavone, Babak Taati
PDF Abstract
SeededGrasp: Language-Guided Grasping in Complex Scenes with Multiple Embodiments
Language-guided grasping in complex scenes across multiple robot embodiments.
Yang Xu, Gurpreet Singh Mukker, Raymond Wang, Jasper Gerigk, Maria Attarian, Igor Gilitschenski
PDF Abstract
Update-Free On-Policy Steering via Verifiers
Update-free on-policy steering via verifiers.
Maria Attarian, Ian Vyse, Claas Voelcker, Jasper Gerigk, Evgenii Opryshko, Anas Almasri, Sumeet Singh, Yilun Du, Igor Gilitschenski
PDF Abstract