SIGIR

ColBERTSaR: Sparsified ColBERT Index via Product Quantization

ColBERTSaR: 通过乘积量化实现稀疏化的 ColBERT 索引

Eugene Yang, Andrew Yates, Dawn Lawrie, James Mayfield, Saron Samuel, Rohan Jha

机构 * Johns Hopkins University（约翰霍普金斯大学） 纠错

AI总结 提出通过乘积量化将 ColBERT 索引转化为真正的倒排索引，显著减小索引大小（比 PLAID 小 50-70%）同时保持检索效果。

Comments 6 pages, 1 figure, accepted at SIGIR 2026 as a short paper

SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling

SOLARIS: 预测性卸载基于潜在表示的推理扩展

Zikun Liu, Liang Luo, Qianru Li, Zhengyu Zhang, Wei Ling, Jingyi Shen, Zeliang Chen, Yaning Huang, Jingxian Huang, Abdallah Aboelela, Chonglin Sun, Feifan Gu, Fenggang Wu, Hang Qu, Huayu Li, Jill Pan, Kaidi Pei, Laming Chen, Longhao Jin, Qin Huang, Tongyi Tang, Varna Puvvada, Wenlin Chen, Xiaohan Wei, Xu Cao, Yantao Yao, Yuan Jin, Yunchen Pu, Yuxin Chen, Zijian Shen, Zhengkai Zhang, Jing Zhu, Dong Liang, Ellie Wen

机构 * Meta AI 纠错

AI总结 本文提出SOLARIS框架，通过预测未来请求中的用户-项目交互嵌入，将昂贵的基础模型推理与关键服务路径解耦，从而在大规模应用中实现实时知识转移，提升服务效率和收益。

Comments Accepted to SIGIR 2026 Industry Track