🏢 NYU

PILAF optimizes human feedback in reward modeling for better LLM alignment by using a novel response sampling strategy that aligns reward modeling with value optimization.

WILDCHAT-50M: Largest public chat dataset refines LLM post-training, showing superior SFT performance with fewer samples.

Boosting diffusion model performance at inference time, this research introduces a novel framework that goes beyond simply increasing denoising steps. By cleverly searching for better noise candidates…