Lei Xu

Researcher, Amazon

Joined

September 2019

Names

Lei Xu (Preferred)

Emails

****@mit.edu (Confirmed)

****@gmail.com (Confirmed)

****@amazon.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

ACL Anthology

Career & Education History

Researcher

Amazon (amazon.com)

2023 – Present

PhD student

Massachusetts Institute of Technology (mit.edu)

2017 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Kalyan Veeramachaneni

2017 – 2022

Expertise

No areas of expertise listed

Publications

Beyond correlation: The impact of human uncertainty in measuring the effectiveness of automatic evaluation and LLM-as-a-judge
Aparna Elangovan, Lei Xu, Jongwoo Ko, Mahsa Elyasi, Ling Liu, Sravan Babu Bodapati, Dan Roth
- ICLR 2025 Poster
- Readers: Everyone
Single Word Change is All You Need: Designing Attacks and Defenses for Text Classifiers
Lei Xu, Sarah Alnegheimish, Laure Berti-Équille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
- CoRR 2024
- Readers: Everyone
Towards Deployable Robust Text Classifiers
Lei Xu
- undefined 2023
- Readers: Everyone
AutoML to Date and Beyond: Challenges and Opportunities
Shubhra Kanti Karmaker Santu, Md. Mahadi Hassan, Micah J. Smith, Lei Xu, Chengxiang Zhai, Kalyan Veeramachaneni
- 2022 (modified: 13 Feb 2023)
- ACM Comput. Surv. 2022
- Readers: Everyone
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu
- 2022 (modified: 16 Apr 2023)
- NAACL-HLT (Findings) 2022
- Readers: Everyone
In Situ Augmentation for Defending Against Adversarial Attacks on Text Classifiers
Lei Xu, Laure Berti-Équille, Alfredo Cuesta-Infante, Kalyan Veeramachaneni
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- ICONIP (3) 2022
- Readers: Everyone
R&R: Metric-guided Adversarial Sentence Generation
Lei Xu, Alfredo Cuesta-Infante, Laure Berti-Équille, Kalyan Veeramachaneni
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- AACL/IJCNLP (Findings) 2022
- Readers: Everyone
Attacking Text Classifiers via Sentence Rewriting Sampler
Lei Xu, Kalyan Veeramachaneni
- CoRR 2021
- Readers: Everyone
Topic-sensitive neural headline generation
Ayana, Ziyun Wang, Lei Xu, Zhiyuan Liu, Maosong Sun
- 2020 (modified: 29 Sept 2024)
- Sci. China Inf. Sci. 2020
- Readers: Everyone
SteganoGAN: High Capacity Image Steganography with GANs
Kevin Alex Zhang, Alfredo Cuesta-Infante, Lei Xu, Kalyan Veeramachaneni
- CoRR 2019
- Readers: Everyone

View all 16 publications