Search papers, labs, and topics across Lattice.
2
4
6
4
Ditch slow, verbose chain-of-thought reasoning: PLUME's latent reasoning slashes inference time by 30x while boosting multimodal embedding performance.
OpenS2S offers researchers a fully transparent, end-to-end LSLM for empathetic speech interaction, filling a critical gap left by increasingly closed-off state-of-the-art models.
