Zian Wang(@zianwang97):Following recent World-Action Model results in robotics, the same ~2B OmniDreams single-view backbone can be fine-tuned into a driving policy. In preliminary closed-loop results, it reduces collision from 6.9% to 4.2% when compared with Alpamayo 1.5, while having roughly 5x fewer parameters.

Zian Wang

@zianwang97

research scientist @NVIDIA, phd candidate @UofT @VectorInst

Joined June 2019

157 Following 1.2K Followers

Zian Wang@zianwang97

2026.06.03 17:21

Following recent World-Action Model results in robotics, the same ~2B OmniDreams single-view backbone can be fine-tuned into a driving policy. In preliminary closed-loop results, it reduces collision from 6.9% to 4.2% when compared with Alpamayo 1.5, while having roughly 5x fewer parameters.