Track manipulation, locomotion and embodied systems.
Search papers, labs, and topics across Lattice.
6
0
6
21
Timbre drift in multi-turn expressive voice agents can be eliminated by replacing implicit context embeddings with explicitly supervised style instructions optimized via rejection sampling and context-aware DPO.
Even top-performing multimodal judges fail to reliably detect errors in specific modalities, revealing hidden blind spots in their evaluations.
VoxAudio revolutionizes vocalized audio synthesis by embedding intelligible speech seamlessly within complex soundscapes, outperforming traditional methods that compromise on clarity and control.
Achieving high-quality audio reconstruction at unprecedented speeds, Qwen-Audio-VAE encodes 32 minutes of audio in just 541 ms.
Full-duplex dialogue systems are often mischaracterized, with many claiming capabilities they cannot deliver due to training limitations.
Current speech generation models still fall short in maintaining consistency and capturing nuanced expressiveness when generating long-form speech, despite advances in high-fidelity synthesis.