Check out our TF2M workshop on Sunday with an amazing list of speakers, panelists, and contributed works: sites.google.com/view/tf2m/sche….

Happening now in Hall A1 at #ICML2024!

Join us for the Workshop on Theoretical Foundations of Foundation Models ICML Conference tomorrow! We have a fantastic list of invited speakers: - Ananda Theertha Suresh - Dan Alistarh - Jason Lee - Kamalika Chaudhuri - Yuandong Tian 1/3

[#ICML2024] Join us at 4:20 pm for an exciting panel to discuss theory and foundation models

Kamalika Chaudhuri’s talk is happening now in Straus 2! Kamalika Chaudhuri Theoretical Foundations of Foundation Models

It was very fun participating in the Theoretical Foundations of Foundation Models. A big thanks to the organizers Berivan Isik Ziteng Sun Banghua Zhu Enric Boix-Adsera Merve Gurel Bo Li Ahmad Beirami Sanmi Koyejo!

Please see an explanation by Zico Kolter as to why ICML tutorial video was initially taken down and is now restored.

Exactly why SaTML Conference exists! Submit there. Let us grow that community.

If the paper is about trustworthy ML, one venue should be screaming at you ----> SaTML Conference Seriously, I have heard from several folks that they had amazing interactions at SaTML Conference You can actually go around and chat with folks and have in depth conversations about their

Great talk from Niloofar Mireshghallah from Allen School at the National Academies Forum on Cyber Resilience meeting, where she talked about LLMs, security, privacy, and "oversharing"

We’re hiring a postdoctoral researcher at FAIR Labs North America to work with us on AI4Math. Please apply at link below and list me and Kaiyu Yang as contacts. Thank you! AI at Meta Yann LeCun Yuandong Tian

Even with preference alignment, LLMs can be enticed into harmful behavior via adversarial prompts 😈. 🚨 Breaking: our theoretical findings confirm: LLM alignment is fundamentally limited! More details, on framework, statistical bounds and phenomenal defense results 👇🏻

If you are attending USENIX Security , say hi to Anvith Thudi and Nick Jia! Anvith will be presenting their work on data-dependent guarantees for DP-SGD. Date: today Wednesday August 14 Time: 1:45pm Track: 7 (Differential Privacy 1)

Excited to talk about privacy and memorizations in LLMs ML Collective tomorrow!! Join us at 10am PT!

Last year, we had so much fun at this workshop! Come join Chhavi Yadav and the rest of us at NeurIPS Conference and send your best interpretability papers here.

This time we have leveled up : accepting papers in 3 tracks - regular, published & position! For more details, check out : interpretable-ai-workshop.github.io & follow my account for updates!

We are excited to announce the **second edition** of our workshop series on interpretability at NeurIPS Conference '24: ⚡️ Interpretable AI: Past, Present, and Future ⚡️ Webpage: interpretable-ai-workshop.github.io Submission Deadline: August 30

We've been informed that some Google searches for NeurIPS conference dates return incorrect dates in the sidebar. To confirm, NeurIPS 2024 is occurring between Monday Dec 9 to Sunday Dec 15, 2024. We encourage all attendees to verify dates directly on our website.

Submit your papers to #AISTATS2025! Enjoy high-quality reviews and join us in an incredible location!

Super pumped to be speaking at the Red Teaming workshop NeurIPS Conference!