Mo Yu (于 墨)
Principal Researcher
Hunyuan, Tencent
E-mail: YuMo AT gmail DOT com (Yu=gf, Mo=lfof)
Embedded Files
Short Bio
I am Mo Yu, a Researcher at Hunyuan, Tencent. My research is mainly focusing on information extraction, question answering, machine reading comprehension and model explainability for NLP.
I received my PhD degree from Harbin Institute of Technology in Jan 2016. Prior to Tencent, I worked as a Research Staff Member at IBM until the year 2021. Before that, I was a visiting student at Johns Hopkins University during 2014-2015 working with Prof. Mark Dredze and Prof. Raman Arora. I was visiting Baidu NLP group during 2012-2013; and was visiting Microsoft Research Asia in 2008 and 2010.
Education
Ph.D. in Computer Science, Harbin Institute of Technology (Jan 2016)
Thesis: Modeling and Learning of Distributed Representations for Natural Language Structures.
Advisor: Tiejun Zhao
M.S. in Computer Science, Harbin Institute of Technology (Jul 2011)
Advisor: Tiejun Zhao
B.S. in Computer Science, Harbin Institute of Technology (Jul 2009)
Research Experience
Principal Researcher, Hunyuan, Tencent (04/2026 – Present)
Principal Researcher, WeChat AI, Tencent (01/2022 – 03/2026)
Research Staff Member, IBM Research AI (02/2017 – 01/2022)
Research staff member of AI Foundations.
Project lead: Towards More Explicit Multi-Hop Question Answering over Texts. (01/2019 – 12/2021)
Project lead: Evidence Aggregation for Open Domain QA. (01/2018 – 01/2019)
Co-PI of the MIT-IBM Joint Project: Deep Rationalization. (01/2018 – 12/2021)
Research Staff Member, IBM Watson (03/2016 – 02/2017)
Research staff member of the Statistical Learning for Question Answering & Discovery Group.
Team lead: the KB-QA team.
Research Assistant, The Center for Language and Speech Processing, Johns Hopkins University (12/2013 – 06/2015)
Visiting scholar at JHU working on learning structured representations for NLP. My advisors are Prof. Mark Dredze and Prof. Raman Arora.
Intern, Natural Language Processing Group, Baidu Inc. (05/2012 – 12/2013)
Research intern working on Dependency Parsing, learning of syntactic representations and online learning algorithms for problems with structured predictions. Some of my work was advised by Prof. Tong Zhang.
Intern, Natural Language Computation Group, MSRA. (07/2010 – 12/2010)
Intern, Web Search and Mining Group, MSRA. (12/2008 – 8/2009)
Selected Publications
Full List of My Publications (By Year)
* indicates authors with equal contribution. § indicates corresponding author. ‡ indicates mentorship.
Memory and Situated Comprehension
[NEW] Junjie Wu‡, Jiangnan Li‡, Yuqing Li‡, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, Mo Yu§. SitEmb-v1. 5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension. Preprint. [PDF] [Models]
Mo Yu*, Qiujing Wang*‡, Shunchi Zhang*‡, Yisi Sang, Kangsheng Pu, Zekai Wei, Han Wang, Liyan Xu, Jing Li, Yue Yu, Jie Zhou. Few-Shot Character Understanding in Movies as an Assessment to Meta-Learning of Theory-of-Mind. ICML 2024. [PDF]
Liyan Xu‡, Jiangnan Li‡, Mo Yu§, Jie Zhou. Fine-Grained Modeling of Narrative Context: A Coherence Perspective via Retrospective Questions. ACL 2024. [PDF]
Mo Yu*, Jiangnan Li*‡, Shunyu Yao, Wenjie Pang, Xiaochen Zhou, Zhou Xiao, Fandong Meng, Jie Zhou. Personality Understanding of Fictional Characters during Book Reading. ACL 2023. [PDF]
Measure of AGI
[NEW] Mo Yu*, Tsz Ting Chung*‡, Chulun Zhou*‡, Tong Li*, Rui Lu*, Jiangnan Li*, Liyan Xu*, Haoshu Lu, Ning Zhang, Jing Li, Jie Zhou. PRELUDE: A Benchmark Designed to Require Global Comprehension and Reasoning over Long Contexts. Preprint. [Website]
Mo Yu*, Lemao Liu*, Junjie Wu*‡, Tsz Ting Chung*‡, Shunchi Zhang*‡, Jiangnan Li, Dit-Yan Yeung, Jie Zhou. The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding. NAACL 2025. [Website]
Junjie Wu‡, Mo Yu§, Lemao Liu, Dit-Yan Yeung§, Jie Zhou. Understanding LLMs’ Fluid Intelligence Deficiency: An Analysis of the ARC Tasks. NAACL 2025. [PDF]
Reading Comprehension & Question Answering
Yisi Sang*‡, Xiangyang Mou*‡, Mo Yu*§, Shunyu Yao, Jing Li, Jeffrey Stanton. TVShowGuess: Character Comprehension in Stories as Speaker Guessing. NAACL 2022.
Xiangyang Mou*‡, Chenghao Yang*‡, Mo Yu*§, Bingsheng Yao, Xiaoxiao Guo, Saloni Potdar, Hui Su. Narrative Question Answering with Cutting-Edge Open-Domain QA Techniques: A Comprehensive Study. TACL 2021.
X. Guo*, M. Yu*, Y. Gao, C. Gan, M. Campbell and S. Chang. Interactive Fiction Game Playing as Multi-Paragraph Reading Comprehension with Reinforcement Learning. EMNLP 2020.
S. Wang*, M. Yu*, T. Klinger, W. Zhang, X. Guo, S. Chang, Z. Wang, J. Jiang, G. Tesauro, M. Campbell. Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering. ICLR 2018.
S. Wang‡, M. Yu, X. Guo, Z. Wang, T. Klinger, W. Zhang, S. Chang, G. Tesauro, B. Zhou. R$^ 3$: Reinforced Reader-Ranker for Open-Domain Question Answering. AAAI 2018.
M. Yu, W. Yin, K. Hasan, C. dos Santos, B. Xiang, B. Zhou. Improved Neural Relation Detection for Knowledge Base Question Answering. ACL 2017.
Representation Learning for NLP
Manling Li‡, Tengfei Ma, Mo Yu, Lingfei Wu, Tian Gao, Heng Ji and Kathleen McKeown. Timeline Summarization based on Event Graph Compression via Time-Aware Optimal Transport. EMNLP 2021.
Z. Lin‡, M. Feng, CN. Santos, M. Yu, B. Xiang, B. Zhou, Y. Bengio. A Structured Self-Attentive Sentence Embedding. ICLR 2017.
M. Yu, M. Dredze, R. Arora, M. Gormley. Embedding Lexical Features via Low-rank Tensors. NAACL 2016.
M. Yu, M. Dredze. Learning Composition Models for Phrase Embeddings. TACL 2015.
M. Gormley*, M. Yu*, M. Dredze. Improved Relation Extraction with Feature-Rich Compositional Embedding Models. EMNLP 2015.
Few-Shot Learning in NLP
M. Yu*, X. Guo*, J. Yi*, S. Chang, S. Potdar, Y. Cheng, G. Tesauro, H. Wang, B. Zhou. Diverse Few-Shot Text Classification with Multiple Metrics. NAACL 2018.
W. Xiong‡, M. Yu, S. Chang, X. Guo, WY. Wang. One-Shot Relational Learning for Knowledge Graphs. EMNLP 2018.
Model Explainability in NLP
M. Yu*, Y. Zhang*, S. Chang*, T. Jaakkola. Understanding Interlocking Dynamics of Cooperative Rationalization. Neurips 2021.
S. Chang*, Y. Zhang*, M. Yu*, T. Jaakkola. Invariant rationalization. ICML 2020.
M. Yu*, S. Chang*, Y. Zhang*, T. Jaakkola. Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control. EMNLP 2019. (My Erdös number becomes 3: Mo Yu → Tommi Jaakkola → Noga Alon → Paul Erdös.)
S. Chang*, Y. Zhang*, M. Yu*, T. Jaakkola. A Game Theoretic Approach to Class-wise Selective Rationalization. NeurIPS 2019.
Y. Bao‡, S. Chang, M. Yu, R. Barzilay. Deriving Machine Attention from Human Rationales. EMNLP 2018.
Other NLP and ML works
Shunyu Yao, Mo Yu, Yang Zhang, Karthik R Narasimhan, Joshua B. Tenenbaum, Chuang Gan. Linking Emergent and Natural Languages via Corpus Transfer. ICLR 2022 Spotlight.
T. Zhao*, M. Yu*, Y. Wang, R. Arora, H. Liu. Accelerated Mini-batch Randomized Block Coordinate Descent Method. NIPS 2014.
L. Jiang, M. Yu, M. Zhou, X. Liu, T. Zhao. Target-dependent Twitter Sentiment Classification. ACL 2011.
Professional Services
Action Editor: ACL Rolling Review (2021-)
Standing Reviewer: TACL (2020-); CL (2021-)
Reviewer (PC Member): ACL 2017-2019; NAACL 2016, 2018; EMNLP 2015, 2017-2020; ICLR 2018, 2019; NIPS 2017-2020; AAAI 2017, 2018; IJCAI 2017-2019
Meta-Reviewer: AAAI 2019 (Senior PC Member); ACL 2020, 2021 (Area Chair); NAACL 2021 (Area Chair); EMNLP 2021, 2022 (Area Chair)
Area Chair: CCL 2017; NAACL 2019; NLPCC 2020; AAAI 2021, 2022, 2023 (Senior Meta-Reviewer); EMNLP 2022 Industrial Track; ICLR 2023
Page updated
Google Sites
Report abuse