418 citations · 3.5k across the 221 of their papers we have counts for
34 papers · 1 filter
HyperSafe: Inference-Time Safety Recovery for Fine-Tuned Language Models
Aznaur Aliev, Carlos Hinojosa, Abdelrahman Eldesokey +3
Safety alignment in large language models can be fragile under fine-tuning, as even benign task adaptation may increase harmful compliance. Existing defenses mainly follow two dire…
Loong: Synthesize Long Chain-of-Thoughts at Scale through Verifiers
Xingyue Huang, Rishabh, Gregor Franke +43
Recent advances in Large Language Models (LLMs) have shown that their reasoning capabilities can be significantly improved through Reinforcement Learning with Verifiable Reward (RL…
Towards Interpretable Deep Local Learning with Successive Gradient Reconciliation
Yibo Yang, Xiaojie Li, Motasem Alfarra +4
Relieving the reliance of neural network training on a global back-propagation (BP) has emerged as a notable research topic due to the biological implausibility and huge memory con…
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
Yibo Yang, Xiaojie Li, Zhongzhu Zhou +4
Current parameter-efficient fine-tuning (PEFT) methods build adapters widely agnostic of the context of downstream task to learn, or the context of important knowledge to maintain.…
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
Wenxuan Zhang, Youssef Mohamed, Bernard Ghanem +3
We propose and study a realistic Continual Learning (CL) setting where learning algorithms are granted a restricted computational budget per time step while training. We apply this…
Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models
Angela Castillo, Jonas Kohler, Juan C. Pérez +5
This paper presents a comprehensive study on the role of Classifier-Free Guidance (CFG) in text-conditioned diffusion models from the perspective of inference efficiency. In partic…
From Categories to Classifiers: Name-Only Continual Learning by Exploring the Web
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Ser-Nam Lim +3
Continual Learning (CL) often relies on the availability of extensive annotated datasets, an assumption that is unrealistically time-consuming and costly in practice. We explore a…
Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges
Peifeng Gao, Qianqian Xu, Yibo Yang +5
Neural Collapse (NC) is a well-known phenomenon of deep neural networks in the terminal phase of training (TPT). It is characterized by the collapse of features and classifier into…
Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants
Yibo Yang, Haobo Yuan, Xiangtai Li +6
How to enable learnability for new classes while keeping the capability well on old classes has been a crucial challenge for class incremental learning. Beyond the normal case, lon…
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
Hasan Abed Al Kader Hammoud, Ameya Prabhu, Ser-Nam Lim +3
We revisit the common practice of evaluating adaptation of Online Continual Learning (OCL) algorithms through the metric of online accuracy, which measures the accuracy of the mode…
Evaluation of Test-Time Adaptation Under Computational Time Constraints
Motasem Alfarra, Hani Itani, Alejandro Pardo +6
This paper proposes a novel online evaluation protocol for Test Time Adaptation (TTA) methods, which penalizes slower methods by providing them with fewer samples for adaptation. T…
Real-Time Evaluation in Online Continual Learning: A New Hope
Yasir Ghunaim, Adel Bibi, Kumail Alhamoud +5
Current evaluations of Continual Learning (CL) methods typically assume that there is no constraint on training time and computation. This is an unrealistic assumption for any real…
Computationally Budgeted Continual Learning: What Does Matter?
Ameya Prabhu, Hasan Abed Al Kader Hammoud, Puneet Dokania +4
Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current…
On Robust Learning from Noisy Labels: A Permutation Layer Approach
Salman Alsubaihi, Mohammed Alkhrashi, Raied Aljadaany +2
The existence of label noise imposes significant challenges (e.g., poor generalization) on the training process of deep neural networks (DNN). As a remedy, this paper introduces a…
Generalizability of Adversarial Robustness Under Distribution Shifts
Kumail Alhamoud, Hasan Abed Al Kader Hammoud, Motasem Alfarra +1
Recent progress in empirical and certified robustness promises to deliver reliable and deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations of DN…
Certified Robustness in Federated Learning
Motasem Alfarra, Juan C. Pérez, Egor Shulgin +2
Federated learning has recently gained significant attention and popularity due to its effectiveness in training machine learning models on distributed data privately. However, as…
On the Robustness of Quality Measures for GANs
Motasem Alfarra, Juan C. Pérez, Anna Frühstück +3
This work evaluates the robustness of quality measures of generative models such as Inception Score (IS) and Fréchet Inception Distance (FID). Analogous to the vulnerability of dee…
Enhancing Adversarial Robustness via Test-time Transformation Ensembling
Juan C. Pérez, Motasem Alfarra, Guillaume Jeanneret +4
Deep learning models are prone to being fooled by imperceptible perturbations known as adversarial attacks. In this work, we study how equipping models with Test-time Transformatio…
ANCER: Anisotropic Certification via Sample-wise Volume Maximization
Francisco Eiras, Motasem Alfarra, M. Pawan Kumar +4
Randomized smoothing has recently emerged as an effective tool that enables certification of deep neural network classifiers at scale. All prior art on randomized smoothing has foc…
DeformRS: Certifying Input Deformations with Randomized Smoothing
Motasem Alfarra, Adel Bibi, Naeemullah Khan +2
Deep neural networks are vulnerable to input deformations in the form of vector fields of pixel displacements and to other parameterized geometric deformations e.g. translations, r…
Training Graph Neural Networks with 1000 Layers
Guohao Li, Matthias Müller, Bernard Ghanem +1
Deep graph neural networks (GNNs) have achieved excellent results on various tasks on increasingly large graph datasets with millions of nodes and edges. However, memory complexity…
Combating Adversaries with Anti-Adversaries
Motasem Alfarra, Juan C. Pérez, Ali Thabet +3
Deep neural networks are vulnerable to small input perturbations known as adversarial attacks. Inspired by the fact that these adversaries are constructed by iteratively minimizing…
Data-Dependent Randomized Smoothing
Motasem Alfarra, Adel Bibi, Philip H. S. Torr +1
Randomized smoothing is a recent technique that achieves state-of-art performance in training certifiably robust deep neural networks. While the smoothing family of distributions i…
Robust Optimization as Data Augmentation for Large-scale Graphs
Kezhi Kong, Guohao Li, Mucong Ding +5
Data augmentation helps neural networks generalize better by enlarging the training set, but it remains an open question how to effectively augment graph data to enhance the perfor…