まいどぅー

About Me

Nuo Xu

Recent News: Building a multimodal Omni-Model @ Meituan LongCat Team.

𐄷 GitHub 🎓 Google Scholar ✉ Email

Research Interests

Large Language Models Multimodal Learning Video Generation Data/Training Systems

This site catalogs ideas, notes, and project updates. I hope some of it proves useful or sparks collaboration.

Experience

Meituan • LongCat Team — Multimodal / Omni-Model
Moonshot AI — Video Generation
DataGrand — OCR

Recent Works

MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning

Yueqian Wang, Songxiang Liu, Disong Wang, Nuo Xu, Guanglu Wan, Huishuai Zhang, Dongyan Zhao, arXiv:2512.06810 (2025)
GitHub Paper

LongCat-Flash-Omni Technical Report

Team, Meituan LongCat, arXiv:2511.00279 (2025)
GitHub Paper

Kimi-VL Technical Report

Team, Kimi, arXiv:2504.07491 (2025)
GitHub Paper

PARAGRAPH2GRAPH: A GNN-based Framework for Layout Paragraph Analysis

Wei, Shu & Nuo Xu, arXiv:2304.11810 (2023)
GitHub Paper