Hasan Abed Al Kader Hammoud

King Abdullah University of Science and Technology — Saudi Arabia

Computer Science · Physical Sciences

8h-index722citations42works1.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Adversarial Robustness in Machine Learning(8), Domain Adaptation and Few-Shot Learning(7), Anomaly Detection Techniques and Applications(6), 3D Shape Modeling and Analysis(4), 3D Surveying and Cultural Heritage(4)

Publications42 total

Unforgotten Safety: Preserving Safety Alignment of Large Language Models with Continual Learning
arXiv (Cornell University)·2025Open Access
Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
arXiv (Cornell University)·2025Open Access
Hala Technical Report: Building Arabic-Centric Instruction & Translation Models at Scale
arXiv (Cornell University)·2025Open Access
Reasoning Vectors: Transferring Chain-of-Thought Capabilities via Task Arithmetic
arXiv (Cornell University)·2025Open Access
Turning the Spell Around: Lightweight Alignment Amplification via Rank-One Safety Injection
ArXiv.org·2025· 1 citedOpen Access
Train Long, Think Short: Curriculum Learning for Efficient Reasoning
arXiv (Cornell University)·2025Open Access
An Embarrassingly Simple Defense Against LLM Abliteration Attacks
ArXiv.org·2025· 1 citedOpen Access
Beyond the Last Answer: Your Reasoning Trace Uncovers More than You Think
arXiv (Cornell University)·2025Open Access
On the Importance of Pretraining Data Alignment for Atomic Property Prediction
ArXiv.org·2025Open Access
Mindstorms in Natural Language-Based Societies of Mind
Computational Visual Media·2025· 4 citedOpen Access
On Pretraining Data Diversity for Self-Supervised Learning
Lecture notes in computer science·2024· 3 cited
Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation
arXiv (Cornell University)·2024Open Access
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
arXiv (Cornell University)·2024· 1 citedOpen Access
Look, Listen, and Attack: Backdoor Attacks Against Video Action Recognition
2024· 9 cited
On Pretraining Data Diversity for Self-Supervised Learning
arXiv (Cornell University)·2024· 2 citedOpen Access
SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?
arXiv (Cornell University)·2024· 3 citedOpen Access
Model Merging and Safety Alignment: One Bad Model Spoils the Bunch
2024· 1 citedOpen Access
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
arXiv (Cornell University)·2023Open Access
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
2023· 7 cited
Don’t FREAK Out: A Frequency-Inspired Approach to Detecting Backdoor Poisoned Samples in DNNs
2023· 4 cited
page 1 of 3Next →

Frequent Co-authors

Bernard Ghanem(39), Adel Bibi(15), Philip H. S. Torr(10), Ameya Prabhu(7), Guohao Li(6), Ser-Nam Lim(5), Philip H. S. Torr(5), Fabio Pizzati(5), Guocheng Qian(4), Hani Itani(4), Kumail Alhamoud(4), Motasem Alfarra(4), Jinjie Mai(3), Ali Thabet(3), Yasir Ghunaim(3), Suliman Abdelwahid(3), Mohammad Rafi Malik(3), Francisco E. Hernández Pérez(3), Hong G. Im(3), Shuming Liu(3)