8 papers
DiSCO: Defending text-to-image generation through distribution-guided contrastive prompt optimization
Tong Zhang, Motasem Alfarra, Carlos Hinojosa +2
As text-to-image generative models advance, they raise critical safety concerns, particularly the generation of Not-Safe-For-Work (NSFW) content such as violence and nudity, furthe…
Distilling Safe LLM Systems via Soft Prompts for On Device Settings
Motasem Alfarra, Cristina Pinneri, Dana Kianfar +2
Deploying safe large language models (LLMs) on resource-constrained edge devices presents a critical challenge: while dual-model systems combining LLMs with guard models provide ef…
Masks Can Be Distracting: On Context Comprehension in Diffusion Language Models
Julianna Piskorz, Cristina Pinneri, Alvaro Correia +3
Masked Diffusion Language Models (MDLMs) have recently emerged as a promising alternative to Autoregressive Language Models (ARLMs), leveraging a denoising objective that, in princ…
Forget Less, Retain More: A Lightweight Regularizer for Rehearsal-Based Continual Learning
Lama Alssum, Hasan Abed Al Kader Hammoud, Motasem Alfarra +2
Deep neural networks suffer from catastrophic forgetting, where performance on previous tasks degrades after training on a new task. This issue arises due to the model's tendency t…
ADVMEM: Adversarial Memory Initialization for Realistic Test-Time Adaptation via Tracklet-Based Benchmarking
Shyma Alhuwaider, Motasem Alfarra, Juan C. Perez +2
We introduce a novel tracklet-based dataset for benchmarking test-time adaptation (TTA) methods. The aim of this dataset is to mimic the intricate challenges encountered in real-wo…
Towards Faster and More Compact Foundation Models for Molecular Property Prediction
Yasir Ghunaim, Andrés Villa, Gergo Ignacz +3
Advancements in machine learning for molecular property prediction have improved accuracy but at the expense of higher computational cost and longer training times. Recently, the J…