We will present this paper tomorrow (Wednesday) 5 - 6:30 PM at poster #379. Please stop by for a chat if you're interested!

Check out our new LLM unlearning work led by Jiabao Ji

Check out our #ICML2024 paper on LLM uncertainty led by Bairu Hou. Yang Zhang will present the paper in person on July 25. Please come and talk to us if you are interested!

WHP a.k.a. Who's Harry Potter?⚡️ is a ML method to unlearn knowledge or biases from training data. Yujian Liu, Yang Zhang, #JameelClinic PI Tommi Jaakkola, and Shiyu Chang propose a new way to extend WHP w/ targeted unlearning arxiv.org/pdf/2407.16997

We will present this paper on Wednesday 16:00 - 17:30 in room Tuttle. Please join us if you are interested. Also, I'm looking for a summer 2025 internship and would love to chat about any potential positions.

We will present this paper tomorrow (Wednesday) from 11 AM to 2 PM at Poster Session 1 East. Please stop by if you are interested in LLM unlearning -- we’d love to connect!

Check out this new work on reasoning model length pruning led by Bairu Hou

New paper led by Li An. We propose an algorithm to defend against piggyback spoofing attacks on LLM watermarking.