From the 1 of 19 linked papers with an AI index.
4 papers · 1 filter
SineProject: Machine Unlearning for Stable Vision Language Alignment
Arpit Garg, Hemanth Saratchandran, Simon Lucey
Multimodal Large Language Models (MLLMs) increasingly need to forget specific knowledge such as unsafe or private information without requiring full retraining. However, existing u…
Structured Initialization for Vision Transformers
Jianqiao Zheng, Xueqian Li, Hemanth Saratchandran +1
Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating thi…
Robust Physical Adversarial Patches Using Dynamically Optimized Clusters
Harrison Bagley, Will Meakin, Simon Lucey +2
Physical adversarial attacks on deep learning systems is concerning due to the ease of deploying such attacks, usually by placing an adversarial patch in a scene to manipulate the…
Enhancing Transformers Through Conditioned Embedded Tokens
Hemanth Saratchandran, Simon Lucey
Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the at…