3 papers
cs.AI2026
META-IR: Meta-Introspective Reasoning for Adaptive Safety Alignment in LLM
Mahabubur Rahman Miraj, Hongyu Huang, Nankun Mu +2
Large Language Models (LLMs) remain vulnerable to jailbreak attacks and harmful-content prompts, particularly under adversarial distribution shifts where static alignment pipelines…
cs.LG2025
GK-SMOTE: A Hyperparameter-free Noise-Resilient Gaussian KDE-Based Oversampling Approach
Mahabubur Rahman Miraj, Hongyu Huang, Ting Yang +3
Imbalanced classification is a significant challenge in machine learning, especially in critical applications like medical diagnosis, fraud detection, and cybersecurity. Traditiona…
cs.LG2025
MENDR: Manifold Explainable Neural Data Representations
Matthew Chen, Micky Nnamdi, Justin Shao +7
Foundation models for electroencephalography (EEG) signals have recently demonstrated success in learning generalized representations of EEGs, outperforming specialized models in v…