Another work at #ICML2024. This work theoretically studies the training and generalization of a one-layer Graph Transformer with trainable positional encoding. Time: Jul. 24th, Wednesday, 1:30-3:00 pm. Location: Hall C 4-9 #506

🔥Excited to share our poster at #ICML2024. This work studies the training dynamics of nonlinear Transformers, together with the In-Context Learning generalization capability of the model. Time: Jul 23rd, Tuesday, 1:30-3:00 pm. Location: Hall C 4-9 #403.

The 3rd AdvML-Frontiers Workshop (AdvMLFrontiers advml-frontier.github.io) is set for #NeurIPS 2024 (NeurIPS Conference)! This year, we're delving into the expansion of the trustworthy AI landscape, especially in large multi-modal systems. Trustworthy ML Initiative (TrustML) LLM Security🚀 We're now

Submit your work and join our workshop to explore the frontier of adversarial machine learning for AI!

Are you a big fan of in-context learning (ICL)? Check out our IBM Research blog post highlighting our ICML Conference paper demystifying ICL. We characterize how ICL learns and generalizes. With Hongkang Li Meng Wang Rensselaer Songtao Lu & Xiaodong Cui Blog: research.ibm.com/blog/demystify…

Our follow-up work on the LLM theory---- the learning and generalization mechanism of Chain-of-Thought (CoT), will be presented in the next two days of the ICML Conference workshops. 1. Fri 26 Jul., Straus 2, HiLD Workshop. 2. Sat 27 Jul., Straus 2, TF2M Workshop.

The Adversarial Machine Learning Rising Star Awards deadline is in two weeks! Submit your application and help us promote your work and research vision! Trustworthy ML Initiative (TrustML) LLM Security ML Safety AI Safety Papers

In our SIGKDD 2024 paper, Changchang Pin-Yu Chen Bingsheng 'Arthur' Yao Dakuo Wang, Jeff and I explore human-centered AI for sepsis early prediction. Join our oral talk tomorrow at 4:30 pm Room 124-125 if you attend KDD this week. OSUengineering The Ohio State University College of Medicine OSU Translational Data Analytics Institute The Ohio State University Wexner Medical Center

Great summary on model merging and mode connectivity. Also adding our work on 1. Mode connectivity and backdoors: openreview.net/forum?id=SJgwz… 2. Mode connectivity and adversarial examples: arxiv.org/abs/2009.02439 3. Safety loss landscape exploration for LLMs: arxiv.org/abs/2405.17374