Hi! I am a first-year PhD student at North Carolina State University, under the guidance of Prof. JUNG-EUN KIM. Previously, I worked as a machine learning scientist in Moffett AI, and was guided by the chief scientist and co-founder of Moffett.AI: Ian En-Hsu Yen. Before that, I got my master's degree from the CS department of San Jose State University in 2021 and was advised by Prof. Mark Stamp. I earned my bachelor's degree from Shandong University in 2016.

I am actively looking for the 2025 summer intern opportunities in the area of Artificial Intellgence, especially the directions of AI Safety and AI Efficiency.

I am also actively looking for the collabrating opportunities in the feild of AI Safety and Efficient AI from Industry, especially the direction of Shadow LLM.

CV / Google Scholar / LinkedIn / Twitter

Shadow LLM Guardians

Address: Raleigh, North Carolina

Email: ljw040426 AT gmail DOT com | jli265 AT ncsu DOT edu

Research Interest

My research interest primarily focusing on the field of AI Safety & AI Efficiency. My specializations include research in data privacy, adversarial attacks, model robustness and uncertainty, as well as Large Language Model (LLM) alignment. Additionally, I am involved in designing research for model compression and red-teaming models.

News

[Dec 2, 2023] One paper is selceted as Oral of FL@FM-NeurIPS 2023
[Nov 7, 2023] Initiated the Shadow-LLM-Guardians Group: https://github.com/Shadow-LLM
[Oct 7, 2023] Two papers are accepted by EMNLP 2023
Serve as the DCAA 2023, AAAI 2024 Reviewer
Serve as official affiliation of New York Universiuty
[Apr 7, 2023] Publicity Chair of the International Workshop on Resource-Efficient Learning for Knowledge Discovery @KDD 2023.
[Oct 3, 2022] Publicity Chair of the first workshop on DL-Hardware Co-Design for AI Acceleration @AAAI 2023.
[Sep 13, 2022] Participate in AI Hardware Summit 2022.
[Sep 7, 2022] Moffett S30 Accelerator wins MLPerf V2.1

Publications

Jianwei Li, Sheng Liu, Qi Lei

Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning

FL@FM-NeurIPS 2023

Workshop Oral

Jianwei Li, Qi Lei, Wei Cheng, Dongkuan Xu

Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models

EMNLP 2023

Main Paper

Jianwei Li, Weizhi Gao, Qi Lei, Dongkuan Xu

Breaking through Deterministic Barriers: Randomized Pruning Mask Generation and Selection

EMNLP 2023

Findings

Shuya Li, Hao Mei, Jianwei Li, Hua Wei, Dongkuan Xu

Toward Efficient Traffic Signal Control: Smaller Network Can Do More

CDC 2023

Main Paper

Jianwei Li, Tianchi Zhang, Ian En-Hsu Yen, Dongkuan Xu

FP8-BERT: Post-Training Quantization for Transformer

DCAA@AAAI 2023

Workshop Paper

Jianwei Li, Han-Chih Chang, Mark Stamp

Free-Text Keystroke Dynamics for User Authentication

Cybersecurity for Artificial Intelligence

Paper

Han-Chih Chang, Jianwei Li, Mark Stamp

Machine Learning-Based Analysis of Free-Text Keystroke Dynamics

Cybersecurity for Artificial Intelligence

Paper

Han-Chih Chang*, Jianwei Li*, Ching-Seh Wu, Mark Stamp

Machine Learning and Deep Learning for Fixed-Text Keystroke Dynamics

Cybersecurity for Artificial Intelligence

Paper

Yan Pang, Ai Shan, Zhen Wang, Mengyu Wang, Jianwei Li, Ji Zhang,Teng Huang, Chao Liu

Sparse‐Dyn: Sparse dynamic graph multirepresentation learning via event‐based sparse temporal attention network

International Journal of Intelligent Systems

Journal Paper

Yan Pang, Teng Huang, Zhen Wang, Jianwei Li, Poorya Hosseini, Ji Zhang, Chao Liu

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

International Journal of Intelligent Systems

Journal Paper

Teaching Assistant

2023.8-2023.12, North Carolina State University, CSC422-Fall 2023, Automated Learning and Data Analysis
2024.1-2024.5, North Carolina State University, CSC422-Spring 2023, Machine Learning

(Last update: Dec 12, 2023.)