Tao Meng

Written as 孟涛

Email: tmeng [at] cs [dot] ucla [dot] edu

I am a research scientist in AI Incubation@Zoom working on LLM pretraining. Prior to that, I received my Ph.D. degree from the Department of Computer Science, UCLA. I was working with Prof. Kai-Wei Chang, the best supervisor in the world, focusing on problems in Natural Language Processing and Machine Learning. Generally, I am working on incorporating constraints in machine learning and natural language processing models. I aim to encode human knowledge into constraints, and control the behaviours of existing models by constrained inference. My resume is available here.

I got my bachelor's degree at IIIS (Yao's Class) in Tsinghua University.

Recent News

* [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.

* [09.2022] Our paper InsNet: An Efficient, Flexible, and Performant Insertion-based Text Generation Model has been accepted by NeurIPS 2022.

* [05.2021] Our paper An Integer Linear Programming Framework for Mining Constraints from Data has been accepted by ICML 2021.

* [04.2021] Our paper GEMNET: Effective Gated Gazetteer Representations for Recognizing Complex Entities in Low-context Input has been accepted by NAACL 2021.

* [04.2020] Our paper SentiBERT: An Effective, Transferable and Interpretable Architecture for Compositional Sentiment Semantics has been accepted by ACL 2020.

* [04.2020] Our paper On the Robustness of Language Encoders against Grammatical Errors has been accepted by ACL 2020.

* [04.2020] Our paper Mitigating Gender Bias Amplification in Distribution by Posterior Regularization has been accepted by ACL 2020.

Not That New News

Publications

[Google Scholar]

Education

Experience

Teaching

 

Awards