Introduction

Overview Download the presentation slides Today in our AI/ML seminar, we were pleased to have Maliha Zahan Chowdhury as the presenter. Maliha is a first-year PhD student in Dr. Zhishuai Guo’s research group. Her talk focused on Direct Preference Optimization (DPO), primarily based on the original 2023 DPO paper. Although the paper was published only three years ago, it has already been cited nearly 8,000 times, reflecting its significant impact on LLM alignment and optimization research. ...

Overview On March 7, 2025, Mosab Rezaei, a PhD student from the CS department, presented on the Forward-Forward algorithm for neural network models, originally proposed by Hinton. The talk explored the biological foundations and intuition behind the algorithm, its working principles, and related follow-up research. During the Q&A session, participants discussed neuron-inspired AI, alternative neural network architectures, and the differences and connections between the Forward-Forward algorithm and traditional feedforward networks.