Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes
Where-OPD uses spatial self-distillation on synthetic scenes to improve multimodal perception.
1 stories, newest first · one card per story
Where-OPD uses spatial self-distillation on synthetic scenes to improve multimodal perception.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views