Search papers, labs, and topics across Lattice.
Affiliation:
2
1
6
5
Diverse LLMs, when strategically routed and collaborating, can collectively achieve significantly fairer outputs than any single model acting alone.
Ditch the slow lane: $R^2$-dLLM turbocharges diffusion language models by slashing decoding steps by up to 75% without sacrificing quality.
