Search papers, labs, and topics across Lattice.
2
0
4
15
Backend delegation is an effective and modular approach for combining natural duplex speech interaction with strong agentic tool-call capabilities and significantly outperforms GPT-realtime-mini and Qwen3-Omni-30B-A3B-Instruct on EVA-Bench.
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.
