Fakhri Karray

University of Waterloo — Canada

Computer Science · Physical Sciences

38h-index8.4kcitations354works2.92yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Face and Expression Recognition(39), Neural Networks and Applications(33), Speech Recognition and Synthesis(18), Fuzzy Logic and Control Systems(18), Topic Modeling(16)

Publications354 total

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
ArXiv.org·2025Open Access
AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection
arXiv (Cornell University)·2025Open Access
PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention
arXiv (Cornell University)·2025Open Access
Expert or not? assessing data quality in offline reinforcement learning
arXiv (Cornell University)·2025Open Access
Y-Shaped Generative Flows
2025Open Access
Temporal convolutional transformer for EEG based motor imagery decoding
Scientific Reports·2025· 1 citedOpen Access
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
arXiv (Cornell University)·2025Open Access
HEXA: Heterogeneity-aware Exact Aggregation for Efficient Fine-Tuning in Federated Learning
2025
GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning
2025
CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval
arXiv (Cornell University)·2025Open Access
Hierarchical Instruction-aware Embodied Visual Tracking
arXiv (Cornell University)·2025Open Access
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
arXiv (Cornell University)·2025Open Access
SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders
arXiv (Cornell University)·2025Open Access
A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models
arXiv (Cornell University)·2025Open Access
MSF-Net: Multi-stage fusion network for emotion recognition from multimodal signals in scalable healthcare
Information Fusion·2025· 6 citedOpen Access
Internet of Health Things: an introduction
Elsevier eBooks·2025· 1 cited
VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration
2025· 1 citedOpen Access
HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs
2025· 1 citedOpen Access
Enhance Hyperbolic Representation Learning via Second-order Pooling
arXiv (Cornell University)·2024Open Access
On the Robustness and Real-time Adaptation of UAV-based Crowd Localization in Complex and High-density Scenes
2024
page 1 of 18Next →

Frequent Co-authors

Mohamed S. Kamel(14), Bob Zhang(5), K. Ponnambalam(5), Adel M. Alimi(4), Keyvan Golestan(4), Wail Gueaieb(4), Xiangqian Wu(3), Jane You(3), Qin Li(3), Ghulam Muhammad(3), Tarek M. Hamdani(3), Shady Shehata(3), S. Jamshid Mousavi(3), Céline Craye(3), Farook Sattar(3), Lobna Nassar(3), Lei Zhang(2), Abdulmotaleb El Saddik(2), Md. Milon Islam(2), Sheikh Nooruddin(2)