#rag
3 briefs tagged #rag.
Research
Researchers adapt Nemotron retrieval stack for Modern Greek
The work adds Greek retrieval training, reranking, grounded generation and a HERA benchmark.
arXiv cs.CL+1 outlet·Aug 6
Research
Researchers release UEmbed multimodal embedding models
UEmbed produces sparse and dense multimodal representations in one decoder-only forward pass.
HF Daily Papers+1 outlet·Aug 6
Research
Researchers release UEmbed multimodal embeddings
UEmbed generates sparse lexical and dense representations in one decoder-only forward pass.
arXiv cs.AI+1 outlet·Aug 4