Search papers, labs, and topics across Lattice.
3
128
9
5
Code LLMs can achieve SOTA performance in agentic tasks by explicitly modeling the dynamic evolution of software logic across different training stages.
Unlock richer autonomous driving models with IEDD, a new dataset of million-level interactive driving segments with strictly aligned language and action.
Muon optimizer now lets you train LLMs twice as fast as AdamW, as validated by a new 3B/16B MoE model called Moonlight.
