Tootfinder

LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation
Ziyan Wang, Yingpeng Du, Zhu Sun, Jieyi Bi, Haoyan Chua, Tianjun Wei, Jie Zhang
https://arxiv.org/abs/2507.10917

LLM-Driven Dual-Level Multi-Interest Modeling for Recommendation
Recently, much effort has been devoted to modeling users' multi-interests based on their behaviors or auxiliary signals. However, existing methods often rely on heuristic assumptions, e.g., co-occurring items indicate the same interest of users, failing to capture user multi-interests aligning with real-world scenarios. While large language models (LLMs) show significant potential for multi-interest analysis due to their extensive knowledge and powerful reasoning capabilities, two key challenge…

T CrB: overview of the accretion history, Roche-lobe filling, orbital solution, and radiative modeling
U. Munari, F. Walter, N. Masetti, P. Valisa, S. Dallaporta, A. Bergamini, G. Cherini, A. Frigo, A. Maitan, C. Marino, G. Mazzacurati, S. Moretti, F. Tabacco, S. Tomaselli, A. Vagnozzi, P. Ochner, I. Albanese
https://arxiv.org/abs/2507.233…

T CrB: overview of the accretion history, Roche-lobe filling, orbital solution, and radiative modeling
(abridged) We aim to derive a robust estimate of the most important parameters describing the physical nature of T CrB, trace the accretion history onto its white dwarf, and account for the unexpected delay in the occurrence of the new outburst: the SAP prior to 1946 was brighter, and it was followed by the nova eruption within 6 months from its conclusion. This time the 2015-2023 SAP has been fainter and two years past its conclusion no new eruption has yet taken place. During 2005-2025, a per…

NAM: A Normalization Attention Model for Personalized Product Search In Fliggy
Shui Liu, Mingyuan Tao, Maofei Que, Pan Li, Dong Li, Shenghua Ni, Zhuoran Zhuang
https://arxiv.org/abs/2506.08382

NAM: A Normalization Attention Model for Personalized Product Search In Fliggy
Personalized product search provides significant benefits to e-commerce platforms by extracting more accurate user preferences from historical behaviors. Previous studies largely focused on the user factors when personalizing the search query, while ignoring the item perspective, which leads to the following two challenges that we summarize in this paper: First, previous approaches relying only on co-occurrence frequency tend to overestimate the conversion rates for popular items and underestim…

Lattice investigation of custodial two-Higgs-doublet model at weak quartic couplings
Guilherme Catumba, Atsuki Hiraguchi, Wei-Shu Hou, Karl Jansen, Ying-Jer Kao, C. -J. David Lin, Alberto Ramos, Mugdha Sarkar
https://arxiv.org/abs/2507.07759

Lattice investigation of custodial two-Higgs-doublet model at weak quartic couplings
The $SU(2){-}$gauged custodial two-Higgs-doublet model, which shares the same global-symmetry properties with the standard model, is studied non-perturbatively on the lattice. The additional Higgs doublet enlarges the scalar spectrum and opens the possibility for spontaneous breaking of the global symmetry. In this work we start by showing the occurrence of spontaneous breaking of the custodial symmetry in a region of the parameter space of the model. Following this, both the spectrum and the r…

Electron-muon conversion in nuclei and rare decays induced by LFV dark photon
Alexey S. Zhevlakov, Sergey Kuleshov, Valery E. Lyubovitskij, Evgenie O. Oleynik
https://arxiv.org/abs/2507.17733

Electron-muon conversion in nuclei and rare decays induced by LFV dark photon
We study lepton flavor violation (LFV) effects occurring in the $e-μ$ conversion in nuclei and in the rare radiative decays $η(η') \to γμe$ of the $η$ and $η'$ mesons with a special impact of the sub-GeV mass vector mediator (dark photon). In the case of the lepton conversion we make estimates for running and future experiments operating with electron beams at fixed target. Obtained results are implemented in analysis of the LFV decays $η(η') \to γμe$. In particular, we derive the fo…

Mixed phases in a Fermi--Hubbard model describing altermagnetism
E. Langmann, J. Lenells
https://arxiv.org/abs/2506.16503 https://arx…

Mixed phases in a Fermi--Hubbard model describing altermagnetism
We study an extension of the 2D Fermi--Hubbard model, which was recently introduced in [Das et al., Phys. Rev. Lett. 132, 263402 (2024)] and shown to describe altermagnetism that can be studied in cold atom systems. Using an updated Hartree--Fock method that can detect instabilities towards phase separation, we show that the model is in a mixed phase in large parts of the parameter regime at half-filling. We argue that the occurrence of a mixed phase is an indication of exotic physics which, in…

RecGPT Technical Report
Chao Yi, Dian Chen, Gaoyang Guo, Jiakai Tang, Jian Wu, Jing Yu, Sunhao Dai, Wen Chen, Wenjun Yang, Yuning Jiang, Zhujin Gao, Bo Zheng, Chi Li, Dimin Wang, Dixuan Wang, Fan Li, Fan Zhang, Haibin Chen, Haozhuang Liu, Jialin Zhu, Jiamang Wang, Jiawei Wu, Jin Cui, Ju Huang, Kai Zhang, Kan Liu, Lang Tian, Liang Rao, Longbin Li, Lulu Zhao, Mao Zhang, Na He, Peiyang Wang, Qiqi Huang, Tao Luo, Wenbo Su, Xiaoxiao He, Xin Tong, Xu Chen, Xunke Xi, Yang Li, Yaxuan Wu, Yeqiu…

RecGPT Technical Report
Recommender systems are among the most impactful applications of artificial intelligence, serving as critical infrastructure connecting users, merchants, and platforms. However, most current industrial systems remain heavily reliant on historical co-occurrence patterns and log-fitting objectives, i.e., optimizing for past user interactions without explicitly modeling user intent. This log-fitting approach often leads to overfitting to narrow historical preferences, failing to capture users' evo…