2 citations · 2 across the 6 of their papers we have counts for
5 papers · 1 filter
LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis +1
Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserv…
DISCO: Disentangled Communication Steering for Large Language Models
Max Torop, Aria Masoomi, Masih Eskandar +1
A variety of recent methods guide large language model outputs via the inference-time addition of steering vectors to residual-stream or attention-head representations. In contrast…
STAR: Stability-Inducing Weight Perturbation for Continual Learning
Masih Eskandar, Tooba Imtiaz, Davin Hill +2
Humans can naturally learn new and varying tasks in a sequential manner. Continual learning is a class of learning algorithms that updates its learned model as it sees new data (on…
ADAPT to Robustify Prompt Tuning Vision Transformers
Masih Eskandar, Tooba Imtiaz, Zifeng Wang +1
The performance of deep models, including Vision Transformers, is known to be vulnerable to adversarial attacks. Many existing defenses against these attacks, such as adversarial t…
ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training
Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar +1
Making deep neural networks robust to small adversarial noises has recently been sought in many applications. Adversarial training through iterative projected gradient descent (PGD…