Search papers, labs, and topics across Lattice.
3
0
6
3
Current vision-language models fail to achieve embodied self-awareness, with none surpassing a 16.8% success rate in real-world interaction tasks.
Stop avatars from looking like they're having a seizure: this method uses autoregressive prediction of appearance latents to create temporally stable and high-fidelity 3D Gaussian avatars.
Finally, VR agents can maintain natural gaze and respond to user movement in real-time, thanks to a novel architecture that achieves state-of-the-art motion quality at over 300 FPS.
