Allen Roush

XTC boosts creative generation diversity by up to 38% while slashing repetition by 71%, all without sacrificing fluency.

DRY cuts verbatim looping by nearly half without sacrificing performance, revolutionizing how we approach text generation in LLMs.

Confidence gating in co-decoding can lead to a substantial 12.6% increase in secure code generation, revealing the critical role of expert model confidence in safety.

High-temperature sampling can enhance diversity in LLM outputs without sacrificing refusal behavior, achieving up to 99% retention of safety responses.