SCOPD: 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
September, 2026
Abstract
We present sparse-context on-policy self-distillation for efficient vision-language models.
Publication
arXiv preprint arXiv:2609.34044
Computer Science PhD Student
Computer Science PhD student researching robust robot manipulation and vision-language-action models