Skip to content
TILens What matters today in tech v0.3.2
Theme

Daily edition · Information Retrieval

The daily ledger

TILens turns technical updates into a focused daily brief: official releases, trusted reporting, and practitioner analysis, deduplicated and organized by topic.

18 Nov 2026 edition

30 articles · 4 sources · 28 papers ·

Top topics: Information Retrieval · AI · AI Research

Information Retrieval AI AI Research

From Relevance to Utility: Rubric Alignment in Yuanbao Search

arXiv:2611.22503v1 Announce Type: new Abstract: Agentic search demands that a search engine move beyond per document relevance ranking to assemble document sets optimized for downstream LLM reasoning. Prior work…

Source: arXiv cs.IR Yu Lu, Lixin Zou, Yangqi Chen, Hui Xu, Qiaolin Xia, Hao Wang, Qianwen Ma, Reed Li, Shuang Zeng, Haijin Liang, Haibo Shi
Information Retrieval AI AI Research

SIMQ: A Single Graph-based Index for Multi-Vector Query

arXiv:2611.22079v1 Announce Type: new Abstract: Multi-vector retrieval models such as ColBERT achieve state-of-the-art effectiveness by representing documents as sets of token-level vectors and scoring via MaxSim, but…

Source: arXiv cs.IR Yifan Lu, Jiabao Jin, Xiaoyao Zhong, Peng Cheng, Xiangyu Wang, Haotian Li, Hua Chen, Junqing Chen, Wei Xi, Heng Tao Shen
Information Retrieval AI AI Research

MIPR: A Benchmark for Reasoning-Intensive Multimodal Intent-to-Product Retrieval with Multi-Category Solutions

arXiv:2611.22509v1 Announce Type: new Abstract: Real-world e-commerce queries often express user intent without naming a target product, and a single intent may be fulfilled by products from multiple categories.…

Source: arXiv cs.IR Qiang Li, Xuan Lu, Jian Ruan, Manxi Lin, Jiacheng Chen, Wen Shen, Zhihua Wei, Xiaoyu Shen, Dan Ou, Xiangheng Kong, Junjun Zheng
Information Retrieval AI AI Research

Complexity and precision in quantum associative retrieval

arXiv:2611.21941v1 Announce Type: cross Abstract: We show that efficient and high-precision quantum associative retrieval is possible with an exponential complexity advantage with respect to the classical brute force…

Source: arXiv cs.IR Carlo A. Trugenberger
Information Retrieval AI AI Research

Deal With It: On Better Schedules for Listwise Reranking

arXiv:2611.22392v1 Announce Type: new Abstract: Listwise LLM rerankers cannot reliably rank hundreds of documents in a single call, and rely on schedules to orchestrate their calls. Parallel schedules split candidates…

Source: arXiv cs.IR Benjamin Clavi\'e, Herumb Shandilya, Hanna Lichtenberg, Aamir Shakir, Makoto P. Kato

Showing 1 day · 30 items available