Tao Meng
Written as 孟涛
Email: mtsomethree [at] outlook [dot] com
I am a Member of Technical Staff at Microsoft AI Superintelligence , where I work on large-scale language model training and reasoning. Most recently, I am a key contributor to MAI-Code-1-Flash , focusing on model training and iteration. I received my Ph.D. in Computer Science from the Department of Computer Science, UCLA in 2024. I worked with Prof. Kai-Wei Chang , the best supervisor in the world, on problems in Natural Language Processing and Machine Learning. My research interests broadly lie in large language models, reasoning, controllability, and incorporating human knowledge into machine learning systems through structured constraints and inference. My resume is available here.
I received my bachelor's degree from IIIS (Yao's Class) at Tsinghua University.
Recent News
* [06.2026] Our model MAI-Code-1-Flash was announced at Microsoft Build 2026. Thanks to the entire team for making it happen!
* [01.2026] I joined the Microsoft AI Superintelligence team as a Member of Technical Staff.
* [09.2024] Three papers are accepted by EMNLP 2024. Thanks my collaborators for the great efforts!
* [05.2024] I passed my defense! Appreciate a lot to my committee: Prof. Adnan Darwiche, Prof. Cho-Jui Hsieh, Prof Yizhou Sun and Prof. Kai-Wei Chang. I will join Zoom to continue my research in large language model pretraining.
* [04.2023] Our paper On the Paradox of Learning to Reason from Data has been accepted by IJCAI 2023.
* [09.2022] Our paper Controllable Text Generation with Neurally-Decomposed Oracle is designated as an Oral at NeurIPS 2022.
Selected Publications
- On the Paradox of Learning to Reason from Data
Honghua Zhang, Liunian Harold Li, Tao Meng, Kai-Wei Chang, Guy Van den Broeck.
Arxiv preprint.
- InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model
Sidi Lu, Tao Meng, Nanyun Peng
Neural Information Processing Systems. NeurIPS 2022.
- Controllable Text Generation with Neurally-Decomposed Oracle
Tao Meng*, Sidi Lu*, Nanyun Peng, Kai-Wei Chang
Neural Information Processing Systems. NeurIPS 2022 (Oral).
- An Integer Linear Programming Framework for Mining Constraints from Data [code] [slides] [video]
Tao Meng, Kai-Wei Chang.
International Conference on Machine Learning. ICML 2021.
- GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input [data] [poster] [slides] [video]
Tao Meng, Anjie Fang, Oleg Rokhlenko and Shervin Malmasi.
Annual Conference of the North American Chapter of the Association for Computational Linguistics. NAACL 2021.
- SentiBERT: An Effective, Transferable and Interpretable Architecture for Compositional Sentiment Semantics
[code]
Da Yin, Tao Meng, Kai-Wei Chang.
Association for Computational Linguistics. ACL 2020.
- On the Robustness of Language Encoders against Grammatical Errors
[code] [video]
Fan Yin, Quanyu Long, Tao Meng, Kai-Wei Chang.
Association for Computational Linguistics. ACL 2020.
- Mitigating Gender Bias Amplification in Distribution by Posterior Regularization
[code] [slides] [video]
Shengyu Jia*, Tao Meng*, Jieyu Zhao, Kai-Wei Chang.
Association for Computational Linguistics. ACL 2020.
- Target Language-Aware Constrained Inference for Cross-lingual Dependency Parsing [code] [poster]
Tao Meng, Nanyun Peng, Kai-Wei Chang
Conference on Empirical Methods in Natural Language Processing. EMNLP 2019.
Education
- Ph.D. (Computer Science), University of California, Los Angeles. 2018.09 - 2024.06
- B.S. (Institute for Interdisciplinary Information Science), Tsinghua University. 2014.08 - 2018.07
Experience
- Member of Technical Staff, Microsoft AI. SuperIntelligence Team, Seattle. 2026 - now
- Research Intern (AI), Meta Inc. AI Integrity, Seattle. 2022.06 - 2022.09
- Applied Scientist Intern, Amazon.com Inc. Alexa Shopping, Seattle. 2020.06 - 2020.09
- Research Intern, Microsoft Research Asia, Natural Languaging Computing, Beijing. 2017.10 - 2018.02
Teaching
- Teaching Assistant, Introduction to Machine Learning, Kai-Wei Chang. UCLA, 2021 Fall
- Teaching Assistant, Introduction to Machine Learning, Kai-Wei Chang. UCLA, 2020 Fall
- Teaching Assistant, Natural Language Processing, Kai-Wei Chang. UCLA, 2020 Spring
Awards
- Amazon PhD Fellowship, 2022