Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
LatentGRM judges preferences in compressed latent space, cutting 8B judge time about 6–7x while matching SFT accuracy.
1 stories, newest first · one card per story
LatentGRM judges preferences in compressed latent space, cutting 8B judge time about 6–7x while matching SFT accuracy.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views