Search papers, labs, and topics across Lattice.
3
0
6
8
Realtime-Venus, a proactive full-duplex interaction system with two separately trained 9B models: Realtime-Venus-Omni for audio-visual interaction and Realtime-Venus-Audio for spoken interaction, which leads the compared models on MMAU, Llama Questions, and Speech CMMLU.
Surpassing human performance in gaze estimation, PaGE closes the human-AI gap by over 60% while remaining lightweight for real-world applications.
Achieve 92% accuracy in identifying who's commanding a robot from 34 meters away by fusing IMU and camera data, a 48% leap over prior art.
