BITEMBED converts LLM backbones to ternary BitNet-style encoders, adapts them with contrastive pre-training and teacher distillation, and produces text embeddings at multiple precisions that perform comparably to full-precision baselines on MMTEB.
arXiv preprint arXiv:2310.18608 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
GenAIR generates LLM-derived archetype embeddings for items and applies behavioral calibration to close the semantic-behavioral gap, yielding performance gains on three real-world datasets when integrated with existing sequential models.
Gryphon unifies Semantic-ID generation with direct item-level scoring in a single encoder-decoder pass, attaining higher Recall@1000 than vanilla and collision-resolved generative retrieval baselines on an industrial music dataset while simplifying the candidate pipeline in a live A/B test.
SilverTorch replaces standalone ANN indexing and filtering with a unified GPU model using a model-based Bloom index and fused Int8 ANN kernel, delivering up to 23.7x throughput and 13.35x cost efficiency gains on industry data.
Truncated embeddings from non-MRL models perform comparably to or better than MRL-trained models for most truncation levels, except heavy truncation of 80% or more.
R²-Searcher introduces fine-grained evidence modeling, retrieval reflection, and R²PO RL to calibrate retrieval-reasoning boundaries and improve multi-hop QA performance.
Qwen3 Embedding models in 0.6B-8B sizes achieve state-of-the-art results on MTEB and retrieval tasks including code, cross-lingual, and multilingual retrieval through unsupervised pre-training, supervised fine-tuning, and model merging on Qwen3 backbones.
citing papers explorer
No citing papers match the current filters.