cs.IR · 2026-06-07 · No. 16

Information Retrieval, 2026-06-07.

3 new papers in cs.IR. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

3 entries
  1. 01

    OneReason Technical Report

    OneRec Team, Biao Yang, Boyang Ding, Chenglong Chu, Dunju Zang, Fei Pan, Han Li, Hao Jiang, Honghui Bao, Huanjie...

    cs.IR · cs.AI · cs.CL

    Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the...

    arxiv.org/abs/2606.06260 · PDF

  2. 02

    Bridging the Semantic-Collaborative Gap: An Asymmetric Graph Architecture for Cold-Start Item Recommendation

    Anh Truong, John Trenkle, Yuanbo Chen, Honghong Zhao, Abdullah Alchihabi, Effy Fang, Michael Tamir

    cs.IR · cs.AI · cs.LG

    Collaborative filtering and graph-based recommendation models are highly effective because they leverage observed user interactions, but this dependence creates a fundamental cold-start challenge when newly added content has no interaction history. In Tubi's production retrieval system, this challenge is further constrained by the serving interface: new content must be assigned a standalone embedding immediately, and the model must also...

    arxiv.org/abs/2606.06225 · PDF

  3. 03

    Knowledge Manifold: A Riemannian Geometric Framework for Semantic Mapping and Geodesic Analysis of Scientific Literature

    Tomonaga Okabe, Kazuhiko Komatsu

    cs.IR · cs.LG

    We present the knowledge manifold: a Riemannian geometric space in which a corpus of documents is arranged according to semantic positional relationships derived from character n-gram TF-IDF representations. The framework proceeds in five tightly coupled stages. First, each document is converted to a character-level n-gram TF-IDF vector (4-7 grams, up to 250,000 features, L2-normalized) and embedded in a two-dimensional knowledge map via...

    arxiv.org/abs/2606.05907 · PDF

This edition is part of The Daily Abstract — cs.IR archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.