Excited to attend #NeurIPS2024 in Vancouver! 🎉 Check out the OPTML Menu of Innovations @ NeurIPS 2024: 🔗 optml-group.com/images/pubpic/…, featuring our latest research on adversarial ML and machine unlearning for generative AI. Looking forward to reconnecting with old friends and

“I thought adding some vague and evasive NOTE would make my racially discriminatory behavior seem less offensive.” - Excuse given by MIT professor who is scheming and racist and now in the eye of the storm. NOTE: Most MIT professors who I know are not discriminative or racist.

🚨 Call to Action: Demand Accountability and Request Refunds from NeurIPS! 🚨 🛑 To NeurIPS Conference: If you don't show your attitude, we will show ours! 🛑 We demand: 1️⃣ A full public apology from NeurIPS and the keynote speaker. 2️⃣ Refunds for all affected attendees. ❗️ Let’s

Honored to receive the Amazon Research Award for advancing machine unlearning techniques--what a fantastic Christmas gift from Amazon Science! Huge thanks to my hardworking students OPTML @MSU. Looking forward to new and fruitful collaborations with Amazon in 2025! MSU College of Engineering

🎉🎉🎉Who needs Santa when your boss is delivering wins like this? 🌟🌟🌟

So grateful for such a babysitting-style tutorial! It took me ten minutes to read but I guess it will take me several months to digest. Thanks Manling!

I'm thrilled to announce that I've been awarded the prestigious IBM PhD Fellowship 2024! IBM Research A heartfelt thank you to my advisor, colleagues, and the IBM award committee for their support and recognition. #IBMPhDFellowship2024 research.ibm.com/university/awa…

Check out our oral paper #ICLR25, led by Hongkang Li and Yihua Zhang, which shows when and why model editing via task vector stays probably effective, with application to LLM unlearning.

(2/n) Oral Paper! Task vector is one of the most popular methods for model editing and model merging. We provide a theoretical framework to understand its generalization and limitations. With Hongkang Li Yihua Zhang Shuai Zhang, Meng Wang sijia.liu x.com/LiHongkang_jnt…

🚨 Excited to attend #ICML2025 and share our latest work (OPTML @MSU) on LLM unlearning -- think of it as AI surgery: removing harmful knowledge while preserving general utility. Catch us at: 🔹 [Paper 1] Tues, July 15 @ 4:30pm PT | E-1108 📄 Invariance Makes LLM Unlearning

Excited to share our ICML '25 work on robust LLM unlearning—“Towards LLM Unlearning Resilient to Relearning Attacks: A Sharpness-Aware Minimization Perspective and Beyond”. 🔗 Paper: arxiv.org/abs/2502.05374 🗓️ Poster: Wed, July 16 @ 4:30 pm PT | E‑2803 🧵

NeurIPS Conference This is great! But will you also consider setting up an official satellite location in China, given the fact that so many great NeurIPS papers come from China and so many Chinese researchers couldn't attend the conference due to the US/Canada Visa issue?

Interesting results! Great job, Junyuan!