Search papers, labs, and topics across Lattice.
Hankuk University of Foreign Studies
3
0
7
LLMs often prefer compromise solutions over binary choices, reshaping our understanding of moral decision-making in AI.
Achieve faster LLM reasoning without sacrificing accuracy by compiling chain-of-thought rationales into reusable functional tokens.
Ditching the standard autoregressive approach lets molecular LLMs generate more chemically valid and structurally coherent molecules.
