1
Light Origins open-sourced LightNav-0, a Qwen3-VL-4B navigation model trained via Real2Sim2Real on 2,000+ scenes and 4,000+ hours of VLA data, leading 10 monocular navigation benches with zero-shot body transfer.
Light Origins open-sourced LightNav-0, a Qwen3-VL-4B navigation model trained via Real2Sim2Real on 2,000+ scenes and 4,000+ hours of VLA data, leading 10 monocular navigation benches with zero-shot body transfer.
Comments
İlk yorumu siz yazın!