Junlin Wang

Duke University

junlin.wang2@duke.edu

[Google Scholar]
[Github]
[Projects]
[CV]

About Me

I am a 2nd year Computer Science PhD at Duke Unviersity, co-advised by Bhuwan Dhingra and Sam Wiseman.

Previously I work closely with Sameer Singh on Machine Learning Interpretaions and Natural Language Processing Projects. I also worked as a NLP research intern in Tencent and Applied AI lab at Comcast in DC supervised by Ferhan Ture.

My research experience has been prmiarily on adversarial methods and interpretations of NLP models. But I am very interested in all kind of NLP projects, including in-context learning and generalization of LLMs.

News

I will be joining Intel Labs as an intern to work on interesting generation problems!
I presented our demo Allennlp Interpret at EMNLP2019 in HK! We also won the Best Demo Award.
I internd at Comcast Applied AI Research Lab summer of 2018.

publications

NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge
Phillip Howard*, Junlin Wang*, Vasudev Lal, Gadi Singer, Yejin Choi, Swabha Swayamdipta.
Arxiv
bib

@misc{howard2023neurocomparatives,
              title={NeuroComparatives: Neuro-Symbolic Distillation of Comparative Knowledge}, 
              author={Phillip Howard and Junlin Wang and Vasudev Lal and Gadi Singer and Yejin Choi and Swabha Swayamdipta},
              year={2023},
              eprint={2305.04978},
              archivePrefix={arXiv},
              primaryClass={cs.CL}
        }

Maestro: A Gamified Platform for Teaching AI Robustness
Margarita Geleta, Jiacen Xu, Manikanta Loya, Junlin Wang, Sameer Singh, Zhou Li and Sergio Gago Masague.
EAAI 2023
bib

@inproceedings{maestro:eaai23,
              author = {Margarita Geleta and Jiacen Xu and Manikanta Loya and Junlin Wang and Sameer Singh and Zhou Li and Sergio Gago Masague},
              title = { {Maestro: A Gamified Platform for Teaching AI Robustness} },
              booktitle = {AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI)},
              year = {2023}
            }

Gradient-based Analysis of NLP Models is Manipulable
Junlin Wang*, Jens Tuyls*, Eric Wallace and Sameer Singh.
EMNLP 2020 Findings
We found that gradient-based interpretation techniques are not faithful
bib blog

@inproceedings{wang2020gradientbased,
                    Author = {Junlin Wang, Jens Tuyls, Eric Wallace and Sameer Singh},
                    Booktitle = {Empirical Methods in Natural Language Processing Findings},                            
                    Year = {2020},
                    Title = {Gradient-based Analysis of NLP Models is Manipulable}}

AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Eric Wallace, Jens Tuyls, Junlin Wang, Sanjay Subramanian, Matt Gardner, and Sameer Singh.
Demo at EMNLP 2019 Best Demo Award
An open-source toolkit built on top of AllenNLP that makes it easy to interpret NLP models.
bib blog

@inproceedings{Wallace2019AllenNLP,
                    Author = {Eric Wallace and Jens Tuyls and Junlin Wang and Sanjay Subramanian and Matt Gardner and Sameer Singh},
                    Booktitle = {Empirical Methods in Natural Language Processing},                            
                    Year = {2019},
                    Title = {AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models}}

Improved regressions with convolutional neural networks for surface enhanced Raman scattering sensing of metabolite biomarkers
William John Thrift; Cuong Quoc Nguyen; Junlin Wang; Jason Ernest Kahn; Ruijun Dong; Andrew Benjamin Laird; Regina Ragan.
SPIE Nanoscience + Engineering
bib

@proceeding{
                            author = { William John Thrift,Cuong Quoc Nguyen,Junlin Wang,Jason Ernest Kahn,Ruijun Dong,Andrew Benjamin Laird,Regina Ragan},
                            title = {Improved regressions with convolutional neural networks for surface enhanced Raman scattering sensing of metabolite biomarkers},
                            volume = {11089},
                            year = {2019},
                            doi = {10.1117/12.2535410},
                            URL = {https://doi.org/10.1117/12.2535410},
                            eprint = {}
                            }

Projects

Link to Some of my Projects