Search papers, labs, and topics across Lattice.
2
0
5
14
This work proposes an efficient method to add streaming ASR capabilities to an existing duplex S2S model by introducing a lightweight ASR head in parallel to the agent text head, enabling real-time user transcription while preserving full-duplex conversational capabilities including turn-taking and barge-in handling.
Multimodal models can now achieve state-of-the-art performance in real-world tasks like document understanding and audio-video comprehension with significantly reduced inference latency thanks to novel token-reduction techniques.
