Welcome to my website!

I (Eli) Chien (簡翌 in Chinese)

Email: elichientwn at gmail dot com

WeChat: elichien1234

(My origami of dragon as the icon :) )

CV (last update 2026-01-08)

Google Scholar X(Twitter) BlueSky

Affiliation:

Dept. of Electrical Engineering, National Taiwan University (NTU)

Graduate Institute of Communication Engineering, National Taiwan University

AI Center of Research Excellence, National Taiwan University (NTU AI-CoRE)

Short Bio

I am an Assistant Professor at National Taiwan University (Electrical Engineering). Previously, I was a visiting researcher at Google (hosted by Peter Kairouz), and a postdoctoral Fellow in the School of Electrical and Computer Engineering at Georgia Institute of Technology, where I am very fortunate to work with Prof. Pan Li. I received my Ph.D. degree in Electrical and Computer Engineering at the University of Illinois Urbana - Champaign. I am very fortunate to work with my advisor Prof. Olgica Milenkovic. Before that, I got my B.S. degree in Electrical Engineering from National Taiwan University where I worked with Prof. I-Hsiang Wang.

My research interests lie in the field of Regulatable AI, in particular privacy and graph-related machine learning. I currently focus on machine unlearning, differential privacy, AI copyright infringement, and their application to graph ML. My other works include geometric learning, including general (hyper)graph neural networks, active learning on (hyper)graphs, and classification in hyperbolic/product spaces.

I spent two summers in Amazon Search and worked with Wei-Cheng Chang, Cho-Jui Hsieh, Jiong Zhang, Jyun-Yu Jiang, Hsiang-fu Yu, and Inderjit Dhillon. Our works are about extracting high-quality node features from raw data with the help of graph information (paper accepted by ICLR 2022) and improving eXtreme multilabel classification methods via side-information with graph learning techniques (paper accepted by ICML 2023). I spent a summer in Nokia Bell Labs and worked with Antonia Maria Tulino and Jaime Llorca. Our work is about active learning on the geometric block model (paper accepted by AAAI 2019).

I've been invited (previously or currently) as an area chair of NeurIPS, and a reviewer of NeurIPS, ICML, ICLR, AISTATS, KDD, TMLR, TheWebConf, SDM, ISIT, CoLLAs, TPDP.

Collaborations: Feel free to drop me an email if you would like to work with me!

For prospective NTU MS/PhD students: If you want to work with me, please fill out this form. 如果您想跟我合作，請填寫 form.

For NTU undergrad students (台大專題生): If you want to work with me, please fill out this form. 如果您想跟我合作，請填寫 form.

Caution: due to a large volume of inquiries, I will likely not respond to emails from students who have not filled out the forms.

News

2026/05: I will serve as an Area Chair for NeurIPS 2026!
2026/05: Two papers accepted by ICML 2026! Thanks and congrats to all my collaborators.
- Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States: This one is about DP hidden-state theory for zeroth-order optimization.
- The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search: This one is about LLM jailbreak. Congrats to the leading students Rongzhe, Peizhi, and Xinjie!
2026/04: I gave a talk at PolyU, Hong Kong on "Machine Unlearning in the LLM era"! Thanks Minxin for hosting me!
2026/04: Three papers (including 1 contributed talk!) in TPDP 2026! Congrats to Amit, Erchi, and all the collaborators!
- MAPLE: Metadata Augmented Private Language Evolution
- Access-Similarity Lens: An Operational Copyright Framework for Generative Models
- DPrivBench: Benchmarking LLMs’ Reasoning for Differential Privacy [contributed talk]
2026/03: I gave a talk at Academia Sinica on "Machine Unlearning in the LLM era"! Thanks Jun-Cheng for hosting me!
2026/02: I gave a talk at NTHU on "Machine Unlearning in the LLM era"! Thanks Tzu-Bin for hosting me!
2026/02: I will give a talk at NTU GICE on the topic: "Trustworthy AI: what is it and my research experience"!
2026/01: I gave a talk at NVIDIA on "Machine Unlearning in the LLM era"! Thanks Frank for hosting me!
2026/01: Our paper "Interplay between cohesin and RNA polymerase II in regulating chromatin interactions and gene transcription," is finally available at Nature Structural & Molecular Biology! Big congrats again to Minji and all the collaborators. It reminds me of the good old visiting times at Jackson Lab :).