Alexander H. Liu

State inertia in full-duplex spoken language models can lead to missed user input, but activation steering effectively mitigates this issue, boosting comprehension rates significantly.

USAD 2.0 achieves state-of-the-art audio understanding by seamlessly integrating self-supervised and supervised learning techniques, scaling to one billion parameters.

Finally, a streaming ASR model matches Whisper's offline transcription quality while maintaining sub-second latency.