Search papers, labs, and topics across Lattice.
3
0
5
9
Aesthetics-guided training enables LeVo 2 to generate songs that not only sound good but also maintain coherence and detail, outperforming existing models.
OpenSearch-VL offers a fully transparent recipe for training state-of-the-art multimodal search agents, finally democratizing access to a capability previously locked behind closed doors.
By tightly coupling reasoning, searching, and generation, Unify-Agent demonstrates that agent-based modeling can substantially improve world knowledge grounding in image synthesis, rivaling closed-source models.
