Postdoctoral Fellowship Opening: Kids Help Phone AI Project
RML is hiring a Post-Doctoral Fellow to work on an agentic AI framework for training frontline mental health support workers, in partnership with Kids Help Phone.
•
1 min read
Latest News
Three RML Papers Accepted to EMBC 2026
RML has three papers accepted to IEEE EMBC 2026 in Toronto, covering multilingual emotion recognition, weakly-supervised breast lesion segmentation, and facial expression synthesis …
•
1 min read
$3.2M Wellcome Grant for Kids Help Phone AI Project
Dr. Khan leads TMU's role in a $3.2M Wellcome-funded project with Kids Help Phone to develop a generative AI simulator for training frontline youth mental health crisis responders.
•
1 min read
RML at ICASSP 2026: PC-SSL for EEG Emotion Recognition
Niki Sheibani and Dr. Khan present PC-SSL at ICASSP 2026 — a predictive coding self-supervised learning framework for EEG-based emotion recognition, achieving state-of-the-art …
•
1 min read
NSERC CREATE Grant: QuantOmics
Dr. Khan leads QuantOmics, Canada's first training pipeline bridging quantum nanotechnology, genomic data science, and AI — funded by NSERC CREATE to train 93 HQP over six years.
•
1 min read
Recent Publications
Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation
EEG-based emotion recognition systems face significant challenges when deployed across different domains due to limited labeled data and individual signal variability. We introduce …
Md Niaz Imtiaz
PC-SSL: A Predictive Coding-Based Self-Supervised Learning Framework for EEG Emotion Recognition
We introduce a predictive coding self-supervised learning (PC-SSL) approach to overcome the limitations of traditional supervised methods hindered by the high cost of labeling EEG …
niki-sheibani
Stress Classification From ECG Signals Using Vision Transformer
Vision transformers have shown tremendous success in numerous computer vision applications; however, they have not been exploited for stress assessment using physiological signals …
zeeshan-ahmad
DynaGuide: A Generalizable Dynamic Guidance Framework for Zero-Shot Guided Unsupervised Semantic Segmentation
We propose DynaGuide, a generalizable dynamic guidance framework that enables zero-shot guided unsupervised semantic segmentation without requiring labeled training data. The …
boujemaa-guermazi
Enhanced Cross-Dataset Electroencephalogram-Based Emotion Recognition Using Unsupervised Domain Adaptation
We propose an enhanced unsupervised domain adaptation framework for EEG-based emotion recognition that achieves robust cross-dataset generalization without requiring target-domain …
Md Niaz Imtiaz