Han Zhao (@hanzhao

Han Zhao

525 posts

Han Zhao

@hanzhao_ml

Assistant Professor @siebelschool; Amazon scholar; Ph.D. @mldcmu; work on trustworthy machine learning and AI.

Champaign, IL

Joined May 2012

Han Zhao
@hanzhao_ml
May 12, 2020
Thrilled to announce that I'll be starting as an Assistant Professor of Computer Science at the University of Illinois at Urbana-Champaign in Fall 2021 @IllinoisCS Huge thanks to all my collaborators who help me make this happen, and looking forward to the future collaborations!
Han Zhao
@hanzhao_ml
Jul 7, 2024
🚨🚨 We are hiring! RT appreciated! Prof. Rui Song (song-ray.github.io) and I will recruit post-doc scientists through Amazon’s post-doc program (amazon.science/postdoctoral-s…).
song-ray.github.io
Rui Song
A highly-customizable Hugo academic resume theme powered by Wowchemy website builder.
78K
Han Zhao
@hanzhao_ml
Jul 27, 2025
Honored to receive the NSF CAREER Award from the Robust Intelligence (RI) program and the CORE grant from the Information Integration and Informatics (III) program! Deep gratitude to my home institute @siebelschool, students, colleagues, and mentors for their unwavering support!
18K
Han Zhao
@hanzhao_ml
Aug 8, 2020
OK great. #NeurIPS2020 reviews out. This is the first time I got a review with sentences that are not even complete. Also, if you "believe" a result is "well-known and highly studied", please provide at least one reference.
Han Zhao
@hanzhao_ml
Sep 26, 2024
Incredibly grateful for the generous support from the NSF and excited to work with the team on enhancing the safety of LLMs! @NSF @IllinoisCDS
Siebel School of Computing and Data Science
@siebelschool
Sep 26, 2024
Congratulations to #ILLINOIS CS professors Han Zhao and Tong Zhang for receiving a $800K NSF award for their project SLES: Monitoring, Improving, and Certifying Safe Foundation Models! 🔸🎉🔹 ▶️ bit.ly/3zv2npr
14K
Han Zhao
@hanzhao_ml
Dec 14, 2024
I wasn't at the keynote speak today but cannot believe this happened at a plenary talk at #NeurIPS. The calling out of the country of origin is completely unnecessary if the intention is to give an example. I hope @NeurIPSConf can take this incident seriously.
NeurIPS Conference
@NeurIPSConf
Dec 14, 2024
NeurIPS acknowledges that the cultural generalization made by the keynote speaker today reinforces implicit biases by making generalisations about Chinese scholars. This is not what NeurIPS stands for. NeurIPS is dedicated to being a safe space for all of us. We want to address
8.7K
Han Zhao
@hanzhao_ml
Apr 28, 2019
"On Learning Invariant Representation for Domain Adaptation" accepted to @icmlconf with high scores. Curious about the tradeoff in learning domain invariant representation for adaptation? Check it here:
arxiv.org
On Learning Invariant Representation for Domain Adaptation
Due to the ability of deep neural nets to learn rich representations, recent advances in unsupervised domain adaptation have focused on learning domain-invariant features that achieve a small...
Han Zhao
@hanzhao_ml
Sep 25, 2023
Happy to share our recent work on understanding linear scalarization vs. multi-objective optimization for multitask learning, to appear at #NeurIPS2023: arxiv.org/pdf/2308.13985…. TL;DR: Is linear scalarization always sufficient for MTL? If not, when will it fail? 1/n
12K
Han Zhao
@hanzhao_ml
Oct 15, 2020
New work: How to defend potential inference attacks on graphs? We propose a method via adversarial learning of representations for this purpose and analyze the potential tradeoff therein. arXiv: arxiv.org/abs/2009.13504 code: github.com/liaopeiyuan/GAL
Han Zhao
@hanzhao_ml
Nov 15, 2025
Proud advisor moment! Huge congrats to Dr. Ruicheng Xian @ruichengxian on a truly wonderful thesis, and many thanks to @thegautamkamath, @Aaroth, Arindam, and Hanghang for serving on his PhD committee. Ruicheng’s PhD work characterizes the fundamental trade-off between group
11K
Han Zhao
@hanzhao_ml
Jul 13, 2020
We will present our recent work on understanding learning language-invariant representations for multilingual machine translations at #ICML2020 on Wednesday. Come and join us! Paper: shorturl.at/zRV19 Poster: shorturl.at/vwz38 Joint work with @JunjieHu12 @risteski_a
Han Zhao
@hanzhao_ml
Sep 19, 2025
🚀Excited to share that our paper “A Snapshot of Influence: A Local Data Attribution Framework for Online RL” has been accepted at #NeurIPS2025 as an Oral 🎉 Online RL powers applications from games and robotics to LLM post-training. Prior work has largely focused on advancing
6.6K
Han Zhao
@hanzhao_ml
May 12, 2024
How to ensure fairness (statistical parity) and privacy (DP) simultaneously? What are the costs of privacy and fairness upon accuracy? Excited to share our #ICML2024 work answering the two questions above! paper: arxiv.org/pdf/2405.04034 code: github.com/rxian/fair-reg…
21K
Han Zhao
@hanzhao_ml
Dec 10, 2023
Heading to New Orleans for #NeurIPS2023 to present the following works with my students and collaborators! Looking forward to catching up with old friends & making new friends!!
6K