Live! Keynote talk by Alina Oprea "Training Secure Agents: Is Reinforcement Learning Vulnerable to Poisoning Attacks?" AdvML-Frontiers Workshop (AdvMLFrontiers ) #NeurIPS2024 East Ballroom C, Vancouver Convention Center advml-frontier.github.io

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

Reminder the deadline to submit a Spotlight (non-archival) track submission to CPAL is TODAY!

Congratulations!

Excited to share that our paper, "Rethinking Machine Unlearning for LLMs", is now published in Nature Machine Intelligence (2025)! 🎉🚀 [rdcu.be/eabfN]. Huge thanks to our amazing collaborators! Yuanshun Yao, Jinghan Jia, Cas (Stephen Casper) @ ICML, Nathalie Baracaldo, Peter Hase,

1/Being in academia is such a privilege: You get to collaborate with insanely talented & passionate students on their journey to upskill themselves. Very excited to share *OpenUnlearning*: a unified, easily extensible framework for unlearning led by Anmol Mekala Vineeth🧵

Honored to receive the prestigious Withrow Rising Scholar Award. Grateful for the unwavering support from my students, advisors, collaborators, nominators, and recommenders. Excited to keep bridging foundational research and real-world impact to advance trustworthy and scalable

Excited to be an invited speaker at the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen mugenworkshop.github.io)! Looking forward to joining this incredible lineup and diving deep into the latest breakthroughs in unlearning for generative AI. Don’t miss out the

🚨 New finding in LLM unlearning: Even with random selection, using just 5% of the forget set can yield a nearly "equivalent" unlearned model--if you're willing to train longer. 💡 This reveals a stronger-than-expected coreset effect, suggesting that unlearning may be "easier"

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.

Seconded! It was a great and rewarding experience collaborating with Pin-Yu Chen on this book. I look forward to using it as a textbook and recommended reading in my future courses.

🚨 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

🎯 ICML 2025 Poster! 📄 “Invariance Makes LLM Unlearning Resilient Even to Unanticipated Downstream Fine-Tuning” 🔗 arxiv.org/abs/2506.01339 🗓️ July 15, 4:30–7:00 pm PT 📍 East Exhibition Hall A-B, #E-1108 🧍‍♂️ I won’t be there in person — but feel free to drop by and chat with my

Thank you INNS for this great honor. I am deeply grateful to my nominator, students, and collaborators who made this recognition possible. Excited to keep advancing the frontiers of scalable and trustworthy AI! OPTML @MSU

🎤 Excited to share that I will be giving two invited talks at #ICCV2025 🔹 Talk 1: VLM Safety via Machine Unlearning at the ICCV'25Tutorial on Responsible Vision-Language Generative Models 🕐 1:25 pm – 2:20 pm| Sunday, Oct 19 | Room 316B 🔹 Talk 2: Robustness of Machine