Search papers, labs, and topics across Lattice.
College of AI
2
0
2
8
PSC achieves up to 700x faster grammar-constrained decoding, making LLMs as efficient as unconstrained decoding for structured output generation.
LLMs can bootstrap their understanding of private APIs by autonomously learning from their own coding attempts, outperforming retrieval-augmented generation by 16% on code generation tasks.
