Portrait of Mengyu Zhou

Mengyu Zhou

Alibaba · Qwen Business UnitResearch Lead

Formerly at Microsoft Research AsiaPrincipal Researcher

Sep 2025–Present

Alibaba · Qwen Business Unit

Research Lead · Frontier Exploration

Mengyu Zhou joined Alibaba's Qwen Business Unit in September 2025 as Research Lead for frontier exploration in the foundation-model group. He leads a team exploring frontier research and bringing it into real-world applications, and is deeply involved in the model training and algorithm stack behind Qwen's consumer applications.

2017–2025

Microsoft Research Asia

Principal Researcher · Data, Knowledge, and Intelligence (DKI) Group

At the Data, Knowledge, and Intelligence (DKI) Group of Microsoft Research Asia, he served as Principal Researcher, advancing spreadsheet intelligence, automated data analysis, and large language models, and contributing to Excel Copilot, Excel Ideas, and Forms Ideas.

Products

  • Qwen · 千问

    Qwen · 千问

    Alibaba's all-in-one AI assistant for conversations, research, document and data analysis, writing, presentations, coding, study, and image and video creation.

  • Excel Copilot

    Excel Copilot

    Copilot in Excel helps users work with data through formula-column suggestions, insights in charts and PivotTables, and highlights of noteworthy data.

  • Excel Ideas

    Excel Ideas

    A core Excel capability spanning table detection and parsing, semantic understanding, and automatic recommendations of analyses and insights.

  • Forms Ideas

    Forms Ideas

    An AI system in Microsoft Forms for survey distribution, response collection, and automatic analysis and recommendations, helping designers improve surveys and understand large response sets.

  • TUNet

    TUNet

    A Tsinghua campus-network app for Android and iOS that automates sign-in and helps users manage and protect their accounts; it was adopted by nearly 20,000 Tsinghua users.

  • Tsinghua Now

    Tsinghua Now

    A Tsinghua campus-life assistant that presents learning-platform updates and schedules as prioritized cards, with utilities such as a GPA calculator and study-room seat lookup.

  • CaμsKit

    CaμsKit

    An information-service suite for large campus events, including enterprise Wi-Fi deployment, a WeChat wall, lottery pages, and Danmaku; it served about 20 large events within one year.

Publications

Corresponding author

2026

SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm ICML 2026

Tianyu Li, Dongchen Han, Zixuan Cao, Haofeng Huang, Mengyu Zhou*, Ming Chen, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang, Gao Huang*

MARCH: Multi-Agent Reinforced Check for Hallucination ACL 2026

Zhuo Li, Yupeng Zhang, Pengyu Cheng*, Jiajun Song, Mengyu Zhou, Hao Li, Shujie Hu, Yu Qin, Erchao Zhao, Xiaoxi Jiang, Guanjun Jiang

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning ACL 2026

Hanbing Liu, Lang Cao, Yuanyi Ren, Mengyu Zhou*, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang

Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models ICLR 2026

Mengni Jia, Mengyu Zhou*, Yihao Liu, Xiaoxi Jiang, Guanjun Jiang

SheetBrain: A Neuro-Symbolic Agent for Accurate Reasoning over Complex and Large Spreadsheets AAAI 2026

Ziwei Wang, Jiayuan Su, Mengyu Zhou*, Huaxing Zeng, Mengni Jia, Xiao Lv, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang

Jupiter: Enhancing LLM Data Analysis Capabilities via Notebook and Inference-Time Value-Guided Search AAAI 2026

Shuocheng Li, Yihao Liu, Silin Du, Wenxuan Zeng, Zhe Xu, Mengyu Zhou*, Yeye He, Haoyu Dong, Shi Han, Dongmei Zhang

2025

MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark NeurIPS 2025

Junjie Xing*, Yeye He*, Mengyu Zhou, Haoyu Dong, Shi Han, Lingjiao Chen, Dongmei Zhang, Surajit Chaudhuri, H. V. Jagadish

TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ Guidance EMNLP 2025

Jingxian Xu, Mengyu Zhou*, Weichang Liu, Hanbing Liu, Shi Han, Dongmei Zhang

Table-LLM-Specialist: Language Model Specialists for Tables using Iterative Fine-tuning EMNLP 2025

Junjie Xing, Yeye He*, Mengyu Zhou, Haoyu Dong, Shi Han, Dongmei Zhang, Surajit Chaudhuri

TableLoRA: Low-rank Adaptation on Table Structure Understanding for Large Language Models ACL 2025

Xinyi He, Yihao Liu, Mengyu Zhou*, Yeye He, Haoyu Dong, Shi Han, Zejian Yuan, Dongmei Zhang

TablePilot: Recommending Human-Preferred Tabular Data Analysis with Large Language Models ACL 2025

Deyin Yi, Yihao Liu, Lang Cao, Mengyu Zhou*, Haoyu Dong, Shi Han, Dongmei Zhang

2024

PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during Large Language Model Fine-tuning EMNLP 2024

Jiaru Zou, Mengyu Zhou*, Tao Li, Shi Han, Dongmei Zhang

CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing EMNLP 2024

Xinyi He, Jiaru Zou, Yun Lin, Mengyu Zhou*, Shi Han, Zejian Yuan, Dongmei Zhang

SPREADSHEETLLM: Encoding Spreadsheets for Large Language Models EMNLP 2024

Yuzhang Tian, Jianbo Zhao, Haoyu Dong*, Junyu Xiong, Shiyu Xia, Mengyu Zhou, Yun Lin, José Cambronero, Yeye He, Shi Han, Dongmei Zhang

TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning EMNLP 2024

Yuan Sui, Jiaru Zou, Mengyu Zhou*, Xinyi He, Lun Du, Shi Han, Dongmei Zhang

Vision Language Models for Spreadsheet Understanding: Challenges and Opportunities ALVR 2024

Shiyu Xia, Junyu Xiong, Haoyu Dong*, Jianbo Zhao, Yuzhang Tian, Mengyu Zhou, Yeye He, Shi Han, Dongmei Zhang

Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study WSDM 2024

Yuan Sui, Mengyu Zhou*, Mingjie Zhou, Shi Han, Dongmei Zhang

Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries AAAI 2024

Xinyi He, Mengyu Zhou*, Xinrun Xu, Xiaojun Ma, Rui Ding, Lun Du, Yan Gao, Ran Jia, Xu Chen, Shi Han, Zejian Yuan, Dongmei Zhang

2023

AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks ACL 2023

Xinyi He, Mengyu Zhou*, Mingjie Zhou, Jialiang Xu, Xiao Lv, Tianle Li, Yijia Shao, Shi Han, Zejian Yuan, Dongmei Zhang

CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement ICLR 2023

Hongwei Han, Mengyu Zhou*, Shi Han, Xiu Li*, Dongmei Zhang

2022

FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information EMNLP 2022

Yijia Shao, Mengyu Zhou*, Yifan Zhong, Tao Wu, Hongwei Han, Shi Han, Gideon Huang, Dongmei Zhang

Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems EMNLP 2022

Jialiang Xu, Mengyu Zhou*, Xinyi He, Shi Han, Dongmei Zhang

Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks IJCAI 2022

Haoyu Dong, Zhoujun Cheng, Xinyi He, Mengyu Zhou, Anda Zhou, Fan Zhou, Ao Liu, Shi Han, Dongmei Zhang

2021

MultiVision: Designing Analytical Dashboards with Deep Learning Based Recommendation IEEE VIS 2021

Aoyu Wu, Yun Wang*, Mengyu Zhou, Xinyi He, Haidong Zhang, Huamin Qu, Dongmei Zhang

Table2Charts: Recommending Charts by Learning Shared Table Representations KDD 2021

Mengyu Zhou, Qingtao Li, Xinyi He, Yuejiang Li, Yibo Liu, Wei Ji, Shi Han, Yining Chen, Daxin Jiang, Dongmei Zhang

2020& earlier

Table2Analysis: Modeling and Recommendation of Common Analysis Patterns for Multi-Dimensional Data AAAI 2020

Mengyu Zhou, Tao Wang, Pengxin Ji, Shi Han, Dongmei Zhang

Collaborative Learning between Cloud and End Devices: An Empirical Study on Location Prediction SEC 2019

Yan Lu, Yuanchao Shu, Xu Tan, Yunxin Liu, Mengyu Zhou, Qi Chen, Dan Pei

The Frame Latency of Personalized Livestreaming Can Be Significantly Slowed Down by WiFi IPCCC 2018

Guoshun Nan, Xiuquan Qiao, Jiting Wang, Zeyan Li, Jiahao Bu, Changhua Pei, Mengyu Zhou, Dan Pei*

Mining Crowd Mobility and WiFi Hotspots on a Densely-Populated Campus PURBA 2017

Mengyu Zhou, Kaixin Sui, Dan Pei, Thomas Moscibroda

MinHash Hierarchy for Privacy Preserving Trajectory Sensing and Query IPSN 2017

Jiaxin Ding, Chien-Chun Ni, Mengyu Zhou, Jie Gao

EDUM: Classroom Education Measurements via Large-Scale WiFi Networks UbiComp 2016

Mengyu Zhou, Minghua Ma, Yangkun Zhang, Kaixin Sui, Dan Pei*, Thomas Moscibroda

Characterizing and Improving WiFi Latency in Large-Scale Operational Networks MobiSys 2016

Kaixin Sui, Mengyu Zhou, Dapeng Liu, Minghua Ma, Dan Pei*, Youjian Zhao, Zimu Li, Thomas Moscibroda

MobiCamp: A Campus-Wide Testbed for Studying Mobile Physical Activities WPA 2016

Mengyu Zhou, Kaixin Sui, Minghua Ma, Youjian Zhao, Dan Pei, Thomas Moscibroda

Awards & Certificates

Awards

  • Tsinghua–Baidu First-Class Scholarship (2016)
  • First Prize and Audience Choice Award, 4th Tsinghua Innovation Contest (2015)
  • Third Prize, 2nd Tsinghua Campus Optimization & Innovation Contest (2013)
  • Progressive Innovation Prize, 13th “Challenge Cup” National Contest of College Students' Extracurricular Scientific & Technological Work (2013)
  • Grand Prize, 11th “Challenge Cup” National Contest of College Students' Extracurricular Scientific & Technological Work (2009)
  • Tsinghua University Second-Class Freshman Scholarship (2008)
  • One of 50 finalists, TopCoder Worldwide High School Tournament (2008)
  • One of 50 finalists, Baidu Astar Programming Contests (2007 & 2008)
  • Gold Medal (3rd place nationwide), China NOI (National Olympiad in Informatics) 2007

Certificates

  • Certificates of completion and verified credentials for more than 50 online courses on Coursera, edX, and Udacity
  • Diplomas de Español como Lengua Extranjera (DELE; Diplomas of Spanish as a Foreign Language), levels A1 and A2
  • One of 50 graduates of the 4th Tsinghua Spark Class, the Program for Talents in Academic & Technological Innovation (2010–2012)
  • Completion certificate, 1st “Intel Cup” Tsinghua Innovation & Entrepreneurship Practice Summer Camp (2009)