Search papers, labs, and topics across Lattice.
Zhejiang University, Tencent Hunyuan
2
0
3
Spatial-Omni achieves superior spatial audio understanding by seamlessly integrating FOA encoding into existing LLMs, outperforming traditional models without compromising general audio processing.
Current audio editing models are failing spectacularly, with an Exact Match Rate below 5% in complex tasks, exposing a critical need for improvement.
