Search
Have an existing account?
Sign In
Tag: retrieval
Linkup ships a sparse retriever that trains on one GPU
SPARSEUP packs a 149M-parameter encoder under Apache 2.0 weights and reports 56.4 average nDCG@10 on BEIR-13.
Google trains a diffusion retriever to widen a single search
Google Research has distilled reinforcement-learned retrieval behaviour into a small diffusion model that fans queries out 12 to…
Perplexity reuses LLM kernels to keep embedding serving cheap
Engineers at Perplexity detail a GPU stack where batch and online embedding workloads borrow prefill and decode paths.