Search papers, labs, and topics across Lattice.
3
0
6
Conversational avatars no longer require latency-heavy cascades: generating speech and full-body gesture end-to-end from shared LLM hidden states runs 5.4脳 faster than two-pass pipelines while matching cascaded teacher fidelity.
Merging concrete visual rollouts with abstract reasoning leads to a 10.6% and 10.9% performance boost on challenging reasoning benchmarks, showcasing the power of hybrid models.
EdgeFM delivers production-grade VLM/LLM inference performance on edge devices, outperforming vendor-specific toolchains by up to 49% while remaining open-source and cross-platform.
