Perplexity's pplx-embed-v2-late keeps per-token vectors for retrieval
Original titleDense embedding models compress each document into one vector, which loses detail as pages get longer or more visual.
AISummary
Perplexity's pplx-embed-v2-late retains a 128-dimensional vector for each token rather than compressing a document into one vector. It scores matches with MaxSim, pairing each query token with its closest document token, which the post presents as preserving detail in long or visually dense pages.
Source: Perplexity · x.comPublished · added here