Quantization Aware Matryoshka Adaptation: Leveraging Matryoshka Learning, Quantization, and Bitwise Operations for Reduced Storage and Improved Retrieval Speed.

@inproceedings{ahemad-2025-quantization, author = {Faizan Ahemad}, editor = {Meeyoung Cha and Carl Yang and Chanyoung Park and Senjuti Basu Roy and Noseong Park and Zhenhui Jessie Li and Carl Yang and Senjuti Basu Roy and Zhenhui Jessie Li and Jaap Kamps and Kijung Shin and Bryan Hooi and Lifang He}, title = {{Quantization Aware Matryoshka Adaptation: Leveraging Matryoshka Learning, Quantization, and Bitwise Operations for Reduced Storage and Improved Retrieval Speed}}, booktitle = {{Proceedings of the 34th ACM International Conference on Information and Knowledge Management, CIKM 2025, Seoul, Republic of Korea, November 10-14, 2025}}, pages = {25--34}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3746252.3761077}, doi = {https://doi.org/10.1145/3746252.3761077} }