KaLM Embedding —Versatile Text Embedding

Explore semantic retrieval and text similarity with KaLM-embedding-multilingual-mini-instruct-v2.5.
The model is loaded on first use. Keep inputs concise for the most responsive public demo.
1 10

Ranked results

Try an example
Query / 查询 Documents / 文档 Results to show Task instruction

About KaLM-Embedding-V2 — KaLM-Embedding-V2, a versatile and compact embedding model that achieves impressive performance in general-purpose text embedding tasks through systematic incentivization of advanced embedding techniques. Model card · Homepage

 
@inproceedings{
    zhao2026kalmembeddingv,
    title={Ka{LM}-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model},
    author={Xinping Zhao and Xinshuo Hu and Zifei Shan and Shouzheng Huang and Yao Zhou and Xin Zhang and Zetian Sun and zhenyu liu and Dongfang Li and Xinyuan Wei and Youcheng Pan and Yang Xiang and Meishan Zhang and Haofen Wang and Jun Yu and Baotian Hu and Min Zhang},
    booktitle={The Fourteenth International Conference on Learning Representations},
    year={2026},
    url={https://openreview.net/forum?id=Y7qzhvWhcz}
}