Search papers, labs, and topics across Lattice.
3
0
6
0
Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate, evaluating audio reasoning, multilingual understanding, tool use, conversational behavior, full-duplex interaction, and safety.
Allocating additional computation during decision-making boosts long-horizon robot manipulation success by significantly enhancing subtask prediction accuracy.
Generalist robot policies can achieve 95% success rates on real-world manipulation tasks by continually learning from a fleet of robots, even in the face of distribution shifts and long-tail failures.
