Paper: arxiv.org/abs/2206.07912 Please check out our presentation at #ICML2022 Hall G, Tuesday 10:30 AM - noon by Linyi Li. Poster: Hall E #213

Check out our #ICML2022 paper: Provable Domain Generalization via Invariant-Feature Subspace Recovery (ISR) [arxiv.org/abs/2201.12919] ISR is a new method for OOD/Domain Generalization & Spurious Correlations, with theoretical guarantees & good empirical performance! 1/14👇

#ICML2022 Given a model that works well on distribution P, what can we say about its performance on distribution Q? Not only you can certify it precisely, but also we can make it scalable to ImageNet models/data! Maurice Weber will talk abt it tomorrow: icml.cc/virtual/2022/s…

Point clouds models are vulnerable to semantic attacks: We provide TPC, a scalable training and robustness certification framework against various types of semantic attacks. #ICML Please check out our presentation at #ICML2022 Hall G, Tuesday 10:30 AM by Linyi Li. Poster: # 211

Congrats #ILLINOIS Computer Science Professor Bo Li! 🔸🏅🔹

Very humbled and grateful to receive 2022 #AdvML Rising Star Awards!! Thanks to all especially our group Bo Li! Will present our efforts & discuss roadmaps for building certifiable ML at sites.google.com/view/advml, KDD 2022 on Aug 15 in DC

Interested in certified ML? I’ll give a talk on large-scale certified trustworthy deep learning at TrustML Young Scientist Seminars (TrustML YSS). Thx, Jingfeng Zhang RIKEN Center for Advanced Intelligence Project for the invitation and hosting! Happening on Tue 9 PM EDT / Wed 10 AM JST trustmlresearch.github.io/online-seminar…

We are organizing a workshop on Trustworthy and Socially Responsible Machine Learning (TSRML) at NeurIPS Conference w/ Linyi Li Huan Zhang Chaowei Xiao Prof. Anima Anandkumar Zico Kolter Plan to join NeurIPS? Submit your work to TSRML! Submission due: Oct 3 AoE tsrml2022.github.io/cfp

Thank you! Btw I’m attending #NeurIPS2022 this week. I’m very happy to chat about research or potential career opportunities or anything - Feel free to DM me :)

#NeurIPS2022 Can we train smoothed DNNs with SOTA deterministic certified robustness? Please visit our poster #233 w/Linyi Li boliweiqi on Wed 11am-1 p.m, Paper: arxiv.org/abs/2210.11620

Wonder how to “certify” the fairness given a trained ML model? Please come to our poster #938 at 4pm-6pm today! Linyi Li Min Tong will be there answer your interesting questions!

#NeurIPS2022 This morning Linyi Li Min Tong will present our paper on core-stable fairness. We model FL as a public decision-making problem and define the core-stable fairness for FL agents, which satisfies proportionality and Pareto-optimality.Poster 809! #fairness #gametheory

So pleased to share my research on trustworthy deep learning systems at the awesome SCP@GaTech! A perfect visit😀

Join us in congratulating Tao Xie for his ACM SIGSOFT 2023 Influential Educator Award! He is a Professor and Chair of the Department of Software Science & Engineering at Peking University, and a Deputy Director of the Key Lab of High Confidence Software Technologies. #ICSE2023

Check out 📢 our COLEP: The first certifiably robust learning-reasoning conformal prediction framework: openreview.net/pdf?id=XN6ZPIN… COLEP is🟰 learning stage for learning semantic concepts ➕ reasoning stage encoding knowledge for logic reasoning via prob. circuits #ICLR2024

Excited to start new journey SFU School of Computing Science Simon Fraser University! Welcome to reach out / drop by @ #Vancouver #Burnaby! Looking to hire multiple PhDs in this cycle in trustworthy AI and interpretable LLM - interested candidates please email me!

Welcome to join our special event on next Tuesday to Thursday 9-11:30am @McLean Management Room (3rd Floor), 515 W Hastings St - just 10-min from NeurIPS venue!

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡