Searcharxiv⌕ Search

arXiv subjects

Xujie Zhou

Publications and source records attributed to Xujie Zhou.

2 recordsLinked to original sources

iBraid group symmetries of iquantum groups via star product

We establish ibraid group symmetries on universal iquantum groups of symmetrizable Kac-Moody type, proving a conjecture of Wang and Zhang. Building on the star product realization of quantum symmetric pairs $(\widetilde{\mathbf U},\widetilde{\mathbf U}^{\imath})$, we relate these symmetries to Lusztig's braid group symmetries, extending the compatibility previously obtained via iHopf algebras in the quasi-split setting. Via the Letzter map $ψ$ from the iquantum group $\widetilde{\mathbf U}^{\imath}$ to the horospherical algebra $\mathcal A\subset \widetilde{\mathbf U}$, we show that the ibraid group symmetry $\widetilde{\mathbf T}'_{i,-1}$ of $\widetilde{\mathbf U}^{\imath}$ transported to $\mathcal A$ coincides with Lusztig's braid group symmetry $\widetilde T_{\mathbf r_i}^{-1}$ on the subalgebra $\mathcal R_{\bullet,i}^{-,r}$. Finally, a mixed product formula, together with a parabolic decomposition, yields an explicit formula for the transported action on the entire horospherical algebra $\mathcal A$.

math.QA↗

MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook

This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We hope it better allows researchers to follow the state-of-the-art in this very dynamic area. Meanwhile, a growing number of testbeds have boosted the evolution of general-purpose large language models. Thus, this year's MARS2 focuses on real-world and specialized scenarios to broaden the multimodal reasoning applications of MLLMs. Our organizing team released two tailored datasets Lens and AdsQA as test sets, which support general reasoning in 12 daily scenarios and domain-specific reasoning in advertisement videos, respectively. We evaluated 40+ baselines that include both generalist MLLMs and task-specific models, and opened up three competition tracks, i.e., Visual Grounding in Real-world Scenarios (VG-RS), Visual Question Answering with Spatial Awareness (VQA-SA), and Visual Reasoning in Creative Advertisement Videos (VR-Ads). Finally, 76 teams from the renowned academic and industrial institutions have registered and 40+ valid submissions (out of 1200+) have been included in our ranking lists. Our datasets, code sets (40+ baselines and 15+ participants' methods), and rankings are publicly available on the MARS2 workshop website and our GitHub organization page https://github.com/mars2workshop/, where our updates and announcements of upcoming events will be continuously provided.

cs.CV↗