Jasper and Stella: distillation of SOTA embedding models

By Dun Zhang, Jia-Cheng Li, Ziyang Zeng, Fu-Yun Wang. 2024

Citations in the corpus

Training Sparse Mixture Of Experts Text Embedding Models (2025, unknown): “For mGTE evaluation, we modify these parameters to use 6% warmup and max gradient norm of 1, matching Zhang et al. (2024).”
IdioLink: Retrieving Meaning Beyond Words Across Idiomatic and Literal Expressions (2026, unknown): “We also include decoder models: Stella (Zhang et al., 2025a) and DRAMA (Ma et al., 2025).”
REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling (2026, unknown): “5B-v5, Zhang et al., 2024), the GN backbones (GTE, Li et al., 2023b; BGE, Xiao et al., 2024) used directly under truncated and chunked mean-pool protocols, and a multi-GN REIGN sweep.”
Scalable text clustering based on word embeddings and noise analysis (2026, unknown): “5 [4], and stella_en_400M_v5 [5].”
Fantastic (small) Retrievers and How to Train Them: mxbai-edge-colbert-v0 Tech Report (2025, unknown): “Finally, we add a third stage to our model pre-training, which is inspired by the Stella [38] model family.”
FreshStack: Building Realistic Benchmarks for Evaluating Retrieval on Technical Documents (2025, unknown): “We have evaluated and included the following families of models: (i) Qwen3 embeddings (596M, 4B, and 8B) [93], (ii) Jina embeddings (V3 and V4) [70, 21], (iii) Stella (1.5B and 400M) [91], (iv) OpenAI text-embedding-3 (small and large) [53], (v) GTE-large-en-v1.”